© 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. 203219
    Prev
    Next
    INDEX
    Explanations

    next followed by nouns

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

    world, notes, definitions

    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
     mentioning
    0.53
     estudiando
    0.51
    𐰃
    0.51
     desarrollando
    0.50
     británico
    0.50
     kostenlos
    0.49
     குறிப்பி
    0.48
    ៀប
    0.48
     skirting
    0.48
     instancias
    0.48
    POSITIVE LOGITS
    CT
    0.50
    Mg
    0.50
     মহা
    0.47
    ్రా
    0.46
    orah
    0.46
    hunt
    0.45
    대가
    0.42
    贼
    0.42
    ilog
    0.42
    ከላከ
    0.41
    Activations Density 0.000%

    No Known Activations