© 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. 196986
    Prev
    Next
    INDEX
    Explanations

    professional private

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

    painful situation

    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
     حقی
    0.47
    <0x0B>
    0.47
     allemand
    0.47
    釘
    0.47
     altında
    0.46
     vững
    0.45
     vehemently
    0.45
     polished
    0.45
     ফেসব
    0.44
     filmu
    0.44
    POSITIVE LOGITS
    ighton
    0.45
    uluh
    0.43
    Const
    0.42
    Lista
    0.42
    })+
    0.42
    WindowManager
    0.42
     const
    0.41
    ensi
    0.41
    jj
    0.41
    })+\
    0.41
    Activations Density 0.000%

    No Known Activations