© 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. 243422
    Prev
    Next
    INDEX
    Explanations

    uncontested edits, not mix, these kinds

    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
     घाल
    0.48
     ɔ
    0.48
     २०२
    0.46
    jš
    0.46
     जब्त
    0.46
     ఇటీవల
    0.45
    რც
    0.45
     있습니다
    0.45
     scorsa
    0.45
    चारी
    0.44
    POSITIVE LOGITS
     Stahl
    0.43
    ACC
    0.41
    longmapsto
    0.41
    铮
    0.41
    **,
    0.40
    谈
    0.39
    Sensor
    0.38
    教学
    0.38
    消耗
    0.38
    ESP
    0.38
    Activations Density 0.002%

    No Known Activations