© 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. 10-GEMMASCOPE-RES-131K
    7. 71022
    Prev
    Next
    INDEX
    Explanations

    how could or if

    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_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
    ).
    -1.16
     ebenfalls
    -1.13
     in
    -1.11
    ਗ਼
    -1.10
    }$,
    -1.09
     Similarly
    -1.09
    )$.
    -1.09
     beberapa
    -1.07
     наконец
    -1.06
    "].
    -1.05
    POSITIVE LOGITS
    咔嚓
    1.54
     poire
    1.39
     soirée
    1.38
     deaktivi
    1.33
    当時
    1.26
    当時は
    1.23
    vemos
    1.22
    𖥸
    1.19
     maillot
    1.19
    swire
    1.19
    Activations Density 0.026%

    No Known Activations