© 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. 7438
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    Global scope, quarterly frequency

    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
    awy
    0.51
    rider
    0.49
    rschein
    0.49
     अनु
    0.47
    มุม
    0.46
    rası
    0.46
    ू
    0.46
     수익
    0.45
    riak
    0.45
     २०२
    0.45
    POSITIVE LOGITS
    টাল
    0.50
     sufr
    0.49
    форд
    0.47
    णिमा
    0.47
     cier
    0.46
     Blanchard
    0.46
    --',
    0.45
     cuyas
    0.44
     gives
    0.44
     aprobación
    0.43
    Activations Density 0.000%

    No Known Activations