© 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. 155048
    Prev
    Next
    INDEX
    Explanations

    word sequences

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

    refer to, implies violence, colors areas

    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
     했던
    0.49
     비밀
    0.47
    secrets
    0.46
    extrait
    0.46
     호
    0.46
    接收
    0.46
     patch
    0.45
     गुप्त
    0.45
     शै
    0.44
    นำ
    0.44
    POSITIVE LOGITS
     Sleeps
    0.43
    !”
    0.41
    স
    0.41
     protons
    0.40
    కపో
    0.40
     normalerweise
    0.40
    Сейчас
    0.40
    羲
    0.40
    ágoras
    0.39
    leqslant
    0.39
    Activations Density 0.000%

    No Known Activations