© 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. 35367
    Prev
    Next
    INDEX
    Explanations

    negative states (stress, hassle)2. or specific concepts (sulfur, Moloch)3. often followed by page numbers or acronyms

    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
     SPINE
    0.42
     inmue
    0.41
    蕨
    0.40
     impacto
    0.40
     incumb
    0.39
     pinta
    0.39
     subside
    0.38
     saepe
    0.38
    蘸
    0.38
    горе
    0.38
    POSITIVE LOGITS
    CC
    0.40
    bok
    0.40
    ems
    0.40
    Aless
    0.40
     प्रकाशन
    0.40
    ҫ
    0.39
    çu
    0.38
     disclosing
    0.38
     প্রচেষ্টা
    0.37
    )}_
    0.37
    Activations Density 0.000%

    No Known Activations