© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34088
    Prev
    Next
    INDEX
    Explanations

    body followed by specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    which
    -3.36
     WHICH
    -2.81
    を作り
    -2.19
    把自己
    -2.16
     probablement
    -2.14
    of
    -2.13
    就去
    -2.13
    ‟
    -2.09
     намного
    -2.09
     MAKING
    -2.06
    POSITIVE LOGITS
    
    2.58
    逡
    2.55
     köpa
    2.44
    ”?
    2.41
     With
    2.41
     เพราะ
    2.31
    膂
    2.31
     exorbitant
    2.30
     太郎
    2.25
    ⇰
    2.25
    Activations Density 0.032%

    No Known Activations