© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164297
    Prev
    Next
    INDEX
    Explanations

    specific phrases after common words

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

    mechanical or verbal confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cependant
    0.48
     difficultés
    0.47
     télévision
    0.46
     Occurrence
    0.45
    并没有
    0.45
    癃
    0.44
     bepaalde
    0.44
    鋈
    0.44
     معين
    0.44
    出现了
    0.43
    POSITIVE LOGITS
    ची
    0.55
    own
    0.50
    certification
    0.49
    capt
    0.45
    xx
    0.42
    conoc
    0.42
    יו
    0.42
    ತಾ
    0.42
    нибудь
    0.42
    ίνουν
    0.42
    Activations Density 0.000%

    No Known Activations