© 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. 175551
    Prev
    Next
    INDEX
    Explanations

    run IOs apps

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

    science claims, crack it, squeeze the

    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
    Moment
    0.44
     চাওয়া
    0.42
    게
    0.42
     순간
    0.42
    ስ
    0.41
    be
    0.41
     invariable
    0.40
    IB
    0.40
    :\
    0.40
    Class
    0.39
    POSITIVE LOGITS
     soglas
    0.50
     encontraron
    0.50
     personalmente
    0.50
     söyl
    0.49
     ελλην
    0.49
     incluem
    0.49
     incluyen
    0.48
     niž
    0.47
     plz
    0.47
     noemen
    0.46
    Activations Density 0.000%

    No Known Activations