© 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. 54579
    Prev
    Next
    INDEX
    Explanations

    life, lottery, things, chains, drinking

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

    legal and official subject lines

    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
     mitigate
    0.47
    ચ
    0.45
    ﺧ
    0.45
    clinton
    0.44
    ︽
    0.42
    although
    0.42
    cfp
    0.41
    Offers
    0.41
    굉
    0.41
    소
    0.40
    POSITIVE LOGITS
     Advanced
    0.46
     kala
    0.46
     and
    0.46
     Snow
    0.45
     Vita
    0.45
     Spy
    0.44
     Low
    0.43
     و
    0.43
     Marty
    0.43
     And
    0.43
    Activations Density 0.000%

    No Known Activations