© 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. 42511
    Prev
    Next
    INDEX
    Explanations

    research them yourself

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

    child, kitten, collide, core, anti

    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
     със
    0.56
    getActive
    0.52
    杲
    0.51
    setPreferredSize
    0.48
    ergewöhn
    0.46
    lma
    0.46
    र्देश
    0.46
    rv
    0.44
     রাজধান
    0.44
    RV
    0.44
    POSITIVE LOGITS
     missed
    0.51
     not
    0.46
    _
    0.45
     fal
    0.45
     mechanics
    0.44
     segments
    0.42
     documental
    0.41
     modes
    0.41
     documentaries
    0.41
     sequence
    0.41
    Activations Density 0.000%

    No Known Activations