© 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. 90231
    Prev
    Next
    INDEX
    Explanations

    risky technique

    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
    keycode
    0.46
    anon
    0.45
    ０
    0.45
     impressive
    0.44
     fortified
    0.44
    وجوان
    0.44
     refuses
    0.44
     ngược
    0.44
    on
    0.44
     recalc
    0.44
    POSITIVE LOGITS
     发
    0.52
     groupBox
    0.49
     Population
    0.46
     Bevölkerung
    0.46
     亻
    0.45
     Invasion
    0.45
     النس
    0.44
     Ceiling
    0.42
    hooting
    0.42
     Clustering
    0.41
    Activations Density 0.001%

    No Known Activations