© 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-16K
    7. 5771
    Prev
    Next
    INDEX
    Explanations

    financial and creative tasks

    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_16k_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
    。
    1.28
    ។
    1.05
    *.
    1.02
    ™.
    1.01
    %.
    1.00
    _.
    0.97
    .
    0.96
    ®.
    0.95
    ].
    0.95
    ।
    0.95
    POSITIVE LOGITS
     असून
    1.00
    していますが
    0.97
    했고
    0.96
     있으며
    0.93
     없고
    0.86
    었고
    0.84
    ，
    0.84
    ،
    0.82
    しましたが
    0.81
    しますが
    0.81
    Activations Density 1.688%

    No Known Activations