© 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. 83190
    Prev
    Next
    INDEX
    Explanations

    saving towards care

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

    ceasefire tension TikTok semicolon

    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
    te
    0.51
    с
    0.50
    be
    0.50
    ة
    0.49
    debt
    0.47
    ch
    0.46
     imb
    0.46
    s
    0.46
    comfort
    0.45
    cee
    0.44
    POSITIVE LOGITS
     தங்கள்
    0.51
     প্রজাত
    0.50
     thaliana
    0.49
     gahet
    0.49
     THOMAS
    0.49
     FOREST
    0.48
     CONSTRAINT
    0.48
     STRING
    0.47
     ওয়েবসাইটে
    0.47
     DEPENDENCIA
    0.47
    Activations Density 0.000%

    No Known Activations