© 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. 107379
    Prev
    Next
    INDEX
    Explanations

    details and instructions

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

    foundation, grounding, jailbreaks

    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
    ir
    0.53
    id
    0.50
    ad
    0.46
    art
    0.46
    ake
    0.46
    ire
    0.44
    ังกฤษ
    0.44
    ur
    0.44
    engkap
    0.44
     большой
    0.41
    POSITIVE LOGITS
     contenus
    0.49
    內容
    0.49
     내용을
    0.48
    的内容
    0.47
     የማይ
    0.46
     compuesto
    0.46
    ጃ
    0.46
     invariants
    0.45
     probleme
    0.45
    の内容
    0.45
    Activations Density 0.002%

    No Known Activations