© 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. 53599
    Prev
    Next
    INDEX
    Explanations

    all however ways find

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

    failures and downsides

    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
     Missouri
    0.45
    াণিত
    0.44
     Stateless
    0.42
     哦
    0.40
    myData
    0.39
    国家的
    0.38
     Harvard
    0.38
    τρι
    0.38
     belum
    0.37
     美国
    0.37
    POSITIVE LOGITS
    莅
    0.46
    йл
    0.46
     shenanigans
    0.45
     barbec
    0.44
    饵
    0.44
     pêche
    0.43
     loophole
    0.43
     disappearance
    0.42
    違反
    0.42
     beaches
    0.42
    Activations Density 0.000%

    No Known Activations