© 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. 131780
    Prev
    Next
    INDEX
    Explanations

    list files, directory path

    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
    遍
    0.46
     παν
    0.40
     Enemy
    0.38
    Enemy
    0.37
    ENEMY
    0.37
    很久
    0.37
    クレジットカード
    0.37
    KYO
    0.36
     interchangeably
    0.36
    ्तर
    0.36
    POSITIVE LOGITS
    ucid
    0.39
    うる
    0.38
    '=>
    0.37
    گیر
    0.36
    magenta
    0.36
    perturbative
    0.36
     osób
    0.36
    ananti
    0.36
    ላ
    0.36
    occurring
    0.36
    Activations Density 0.000%

    No Known Activations