© 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. 145050
    Prev
    Next
    INDEX
    Explanations

    here, view, one, then

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

    talking about

    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
     $+$
    0.52
    atán
    0.51
     Fundação
    0.49
     Já
    0.47
     tensão
    0.47
    ),],
    0.46
    ";}
    0.46
     \%
    0.46
     $+
    0.46
    ◟
    0.46
    POSITIVE LOGITS
     lights
    0.47
    ኪ
    0.44
     Lights
    0.44
     rapeseed
    0.44
    Anton
    0.43
    Wales
    0.43
    Zach
    0.43
    Small
    0.42
     opposite
    0.42
     workplace
    0.42
    Activations Density 0.000%

    No Known Activations