© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45923
    Prev
    Next
    INDEX
    Explanations

    instructions and lists

    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
     processo
    0.47
     Similarly
    0.46
    How
    0.46
     Arbeiten
    0.44
    Why
    0.43
    I
    0.43
    面積
    0.42
    C
    0.42
    Similarly
    0.42
     Process
    0.42
    POSITIVE LOGITS
    尼亚
    0.48
     whatnot
    0.47
     amigos
    0.45
    ።
    0.45
     exploits
    0.45
     quirky
    0.44
     sporting
    0.44
     delicacies
    0.44
     друзьями
    0.44
     bandit
    0.43
    Activations Density 0.002%

    No Known Activations