© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178888
    Prev
    Next
    INDEX
    Explanations

    listing, content, access, required, member, evaluate

    np_acts-logits-general · gemini-2.5-flash-lite

    limits, highest values, timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    闓
    0.50
    lacian
    0.50
    ᙱ
    0.49
    λικό
    0.49
    мина
    0.48
    ждает
    0.47
    惪
    0.47
    グランド
    0.47
    ಂಡ
    0.45
    드시
    0.45
    POSITIVE LOGITS
     ovo
    0.51
     Instructor
    0.51
     r
    0.48
     nh
    0.46
    ---------
    0.45
     seh
    0.44
     surm
    0.44
     Investigators
    0.44
     contento
    0.44
    ru
    0.44
    Activations Density 0.000%

    No Known Activations