© 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. 142911
    Prev
    Next
    INDEX
    Explanations

    light, think, Five, retain, speak

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

    certainty or possibility

    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
    at
    0.47
    galactos
    0.46
    ?!
    0.46
    !,
    0.46
    !".
    0.45
    financing
    0.44
    +,
    0.44
    aaaaaaaa
    0.43
    形成了
    0.43
     waited
    0.43
    POSITIVE LOGITS
     bathrobe
    0.52
    ոն
    0.48
     kiles
    0.47
     особенности
    0.47
    ރު
    0.46
    ම
    0.45
     ridicule
    0.45
    ുള്ള
    0.45
    툼
    0.45
     sonda
    0.44
    Activations Density 0.000%

    No Known Activations