© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77981
    Prev
    Next
    INDEX
    Explanations

    social media trends

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Redis
    0.48
    보
    0.47
    Player
    0.47
    Bolt
    0.46
    Damage
    0.45
    BOX
    0.44
    elog
    0.44
     recieve
    0.44
    脉
    0.43
    Real
    0.43
    POSITIVE LOGITS
    цы
    0.44
    uidade
    0.44
     Confucian
    0.44
     cosmopolitan
    0.43
    inderella
    0.43
     ethnicity
    0.42
     jabatan
    0.42
     Chancery
    0.42
     debt
    0.42
     они
    0.41
    Activations Density 0.017%

    No Known Activations