© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15008
    Prev
    Next
    INDEX
    Explanations

    contact details

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags contact‐info cues—headings and tokens like “Office,” “Email,” “Fax,” “Tel,” “@,” etc., that occur in address/phone/email blocks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -1.51
    styleUrls
    -1.45
    oglobin
    -1.38
    ]})
    -1.32
     }));
    -1.32
     tinha
    -1.32
     }],
    -1.32
    aning
    -1.31
     éton
    -1.31
     brillantes
    -1.29
    POSITIVE LOGITS
     if
    1.65
     also
    1.53
     επίσης
    1.52
     there
    1.42
     również
    1.41
     while
    1.38
     aswell
    1.30
    ,
    1.28
     until
    1.27
    adalu
    1.23
    Activations Density 0.045%

    No Known Activations