© 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. 179109
    Prev
    Next
    INDEX
    Explanations

    after certain words

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

    initial exploration, reporting changes

    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
     gets
    0.49
     destroys
    0.49
     profe
    0.47
    ल्हे
    0.47
     で
    0.46
     secrecy
    0.45
     比
    0.44
     releg
    0.44
     בי
    0.43
    📮
    0.43
    POSITIVE LOGITS
     averigu
    0.50
    주의
    0.48
    :
    0.47
    i
    0.47
    ewerk
    0.46
    Tensor
    0.46
    hier
    0.45
    Pooled
    0.45
    arası
    0.45
    성의
    0.44
    Activations Density 0.001%

    No Known Activations