© 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-65K
    7. 6851
    Prev
    Next
    INDEX
    Explanations

    options first

    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_65k_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
    8
    0.53
    5
    0.47
    7
    0.46
     (
    0.43
    4
    0.42
    6
    0.42
    2
    0.41
     (!)
    0.40
     Admissions
    0.39
    9
    0.39
    POSITIVE LOGITS
    茠
    0.42
    🖒
    0.41
    푞
    0.38
    洍
    0.38
     pett
    0.38
    Editar
    0.38
    䓶
    0.38
    涹
    0.38
     misery
    0.37
     тихо
    0.36
    Activations Density 0.404%

    No Known Activations