© 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. 165749
    Prev
    Next
    INDEX
    Explanations

    suite comparison longer standard available risks

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

    explains vulnerability code

    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
    rant
    0.57
     ኣ
    0.56
     recc
    0.55
    리
    0.55
    St
    0.53
     지역
    0.53
    RTC
    0.53
    Cs
    0.50
    ..)
    0.50
    B
    0.50
    POSITIVE LOGITS
     intervened
    0.50
     দুর্দ
    0.45
    figured
    0.43
    ികിത്സ
    0.43
    प्लाई
    0.42
     ventured
    0.42
    चीन
    0.42
     maximizing
    0.42
    കസ
    0.42
     horrors
    0.41
    Activations Density 0.000%

    No Known Activations