© 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. 172235
    Prev
    Next
    INDEX
    Explanations

    entering a response file handlers curse

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

    unusual or perfect states

    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
    ת
    0.50
    0.46
     論
    0.45
    初期
    0.45
    it
    0.44
    I
    0.44
    ו
    0.44
    悹
    0.44
     ფედერ
    0.44
    맟
    0.43
    POSITIVE LOGITS
     perfekte
    0.54
     mutilated
    0.54
     perfekt
    0.54
     pathogenic
    0.51
     stunned
    0.47
     thwarted
    0.47
     anomalous
    0.46
    named
    0.46
     perfect
    0.45
     proactive
    0.45
    Activations Density 0.000%

    No Known Activations