© 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. 199830
    Prev
    Next
    INDEX
    Explanations

    heaven, battle, payments, law

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

    There's a lot of

    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
    rice
    0.50
    paddle
    0.49
    醝
    0.47
    頖
    0.47
    sampling
    0.47
    Bromo
    0.46
    季度
    0.46
    getMetering
    0.46
    㗽
    0.46
    lini
    0.45
    POSITIVE LOGITS
     begr
    0.50
     Nazis
    0.49
     plea
    0.48
     enraged
    0.46
     encamp
    0.45
     pleas
    0.45
     incidents
    0.45
     recovers
    0.45
     stabilizes
    0.45
     entonces
    0.45
    Activations Density 0.000%

    No Known Activations