© 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. 8056
    Prev
    Next
    INDEX
    Explanations

    how things perform or interact

    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
    0
    0.55
    ש
    0.50
    个
    0.50
    0.49
    s
    0.47
    .;
    0.45
    5
    0.44
    ه
    0.43
    events
    0.43
     individuales
    0.43
    POSITIVE LOGITS
     prohibitive
    0.48
    यों
    0.47
    ിലും
    0.47
    iyordu
    0.46
    uper
    0.45
    ಸ್ಥ
    0.45
    planetary
    0.44
     semidefinite
    0.44
     QCD
    0.44
     स्वप्
    0.44
    Activations Density 0.000%

    No Known Activations