© 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. 54477
    Prev
    Next
    INDEX
    Explanations

    control, difference, impact

    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
     invokes
    0.57
     equivoc
    0.55
     invoking
    0.53
     praises
    0.49
     invoked
    0.48
     accuses
    0.47
    ช
    0.45
     describes
    0.44
     descripción
    0.44
     unlocks
    0.44
    POSITIVE LOGITS
    AT
    0.40
    ما
    0.40
    م
    0.38
     Limit
    0.38
     владе
    0.38
    endem
    0.38
    onial
    0.38
     maintien
    0.37
    iminary
    0.37
    ᄋ
    0.37
    Activations Density 0.000%

    No Known Activations