© 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. 136053
    Prev
    Next
    INDEX
    Explanations

    parentheses and code blocks

    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
    "
    0.51
     Verm
    0.43
     informational
    0.42
     URLs
    0.42
     wording
    0.42
     customs
    0.41
     "
    0.41
     seems
    0.41
     Addressing
    0.40
     inbound
    0.40
    POSITIVE LOGITS
    teile
    0.50
    𝐰
    0.50
    мато
    0.46
    malign
    0.46
    vý
    0.45
    潛行
    0.45
    bollywood
    0.44
    parents
    0.44
    studentid
    0.44
    anhyd
    0.44
    Activations Density 0.004%

    No Known Activations