© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42525
    Prev
    Next
    INDEX
    Explanations

    dialogue responses

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

    describing actions or states

    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
    하실
    0.54
     government
    0.45
     PAINT
    0.45
     realty
    0.44
    𝗶
    0.44
     SHIP
    0.43
    ir
    0.43
    デジタル
    0.42
    ಿಸಬಹುದು
    0.42
     delineate
    0.42
    POSITIVE LOGITS
     roue
    0.50
    }}(\
    0.44
     Madness
    0.43
     madness
    0.42
     Predators
    0.42
     sau
    0.41
     અત
    0.41
     hacía
    0.41
     मालिक
    0.40
     paréntesis
    0.40
    Activations Density 0.000%

    No Known Activations