© 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. 40-GEMMASCOPE-2-RES-262K
    7. 168936
    Prev
    Next
    INDEX
    Explanations

    cyberpunk anime and tributaries

    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_40_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
    ުރު
    0.39
     Herrmann
    0.38
     Autodesk
    0.37
     batería
    0.36
    传
    0.36
     exceedingly
    0.36
     Hü
    0.36
     ছিল
    0.35
     ಕಂಡ
    0.35
     Agustín
    0.35
    POSITIVE LOGITS
     AKA
    0.40
     patri
    0.38
     поряд
    0.36
    Approval
    0.36
     πολι
    0.36
     ONLY
    0.36
    ਥ
    0.35
     psychologically
    0.35
    心理
    0.35
    patri
    0.35
    Activations Density 0.002%

    No Known Activations