© 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. 216787
    Prev
    Next
    INDEX
    Explanations

    Kabi USA

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

    harmful explicit content

    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
    ו
    0.50
    ازی
    0.47
     vento
    0.47
    ᱣ
    0.46
    өг
    0.46
     অঞ্জু
    0.46
    discovered
    0.46
     istek
    0.45
    ลม
    0.44
    OGND
    0.44
    POSITIVE LOGITS
    .
    0.52
     Attacks
    0.43
    \,.
    0.42
     principes
    0.40
     initialState
    0.39
    aktor
    0.39
     salut
    0.38
     Cube
    0.38
     escalating
    0.38
     Série
    0.38
    Activations Density 0.000%

    No Known Activations