© 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. 155894
    Prev
    Next
    INDEX
    Explanations

    lets me, doesn't, heal up, enemy and

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

    horror story diary

    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
    p
    0.55
    R
    0.54
    class
    0.53
    el
    0.53
    s
    0.53
    summer
    0.52
    uv
    0.52
    nd
    0.51
    ir
    0.50
    RT
    0.50
    POSITIVE LOGITS
    ດ້
    0.52
     ఫి
    0.50
    ഭ്യാസ
    0.48
     ഇടപെ
    0.48
     аспек
    0.47
     перспек
    0.47
     перспекти
    0.47
    надцать
    0.47
     onem
    0.46
     ۱
    0.46
    Activations Density 0.000%

    No Known Activations