© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7895
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    mentions of web links and explicit website references (URLs and related link indicators).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LoginActivity
    0.21
    َنْ
    0.20
    Gosudarstvennyj
    0.20
    PATCH
    0.20
    TimeSeries
    0.19
    SScript
    0.19
    DepartTime
    0.19
    𒅆
    0.19
    ्लो
    0.19
    Pyrimidine
    0.19
    POSITIVE LOGITS
    u
    0.22
    ↵↵
    0.20
     Interestingly
    0.19
     They
    0.19
    re
    0.19
     However
    0.19
    ı
    0.19
    <h3>
    0.18
    ă
    0.18
     ata
    0.18
    Activations Density 2.569%

    No Known Activations