© 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. 138148
    Prev
    Next
    INDEX
    Explanations

    express conditional possibilities

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

    prompts about states or actions

    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
     obviamente
    0.48
    ’
    0.48
    órmula
    0.46
     заявления
    0.45
     includes
    0.45
     qualified
    0.45
     শুভে
    0.44
     огромное
    0.44
     заявление
    0.43
    ì
    0.42
    POSITIVE LOGITS
    之后
    0.45
    และการ
    0.44
    走出
    0.44
    และความ
    0.44
     중심
    0.43
     Unterricht
    0.43
    راهيم
    0.43
    nętr
    0.42
     bezpie
    0.42
    民眾
    0.42
    Activations Density 0.003%

    No Known Activations