© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13325
    Prev
    Next
    INDEX
    Explanations

    perm and geom

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

    The neuron activates on occurrences of the subword “perm” as part of the chemical name “permanganate.”

    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
    </h5>
    -2.73
    d
    -2.38
    </td>
    -2.34
    .
    -2.27
    !");
    
    -2.16
    ⢓
    -2.13
    }
    -2.09
     другие
    -2.09
     We
    -2.08
     '../../../../
    -2.05
    POSITIVE LOGITS
    他们是
    2.70
     selben
    2.69
     '
    2.64
    躋
    2.47
     =
    2.42
    不论
    2.42
     şi
    2.39
    当时的
    2.38
    9
    2.31
    ться
    2.27
    Activations Density 0.003%

    No Known Activations