© 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. 75745
    Prev
    Next
    INDEX
    Explanations

    future actions

    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
     grill
    0.46
     hypertensive
    0.44
     disconnection
    0.42
     వ
    0.41
     vertebrae
    0.41
     transverse
    0.40
     ایکسپریس
    0.40
     coil
    0.40
     asynchronous
    0.40
     decoupled
    0.39
    POSITIVE LOGITS
    ab
    0.53
    ac
    0.52
    ib
    0.52
    im
    0.52
     Verantwortung
    0.52
    te
    0.50
    饵
    0.49
    un
    0.49
    〢
    0.49
    u
    0.49
    Activations Density 0.000%

    No Known Activations