© 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. 173160
    Prev
    Next
    INDEX
    Explanations

    American Academy, playable characters, Rescue Party

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

    resource extraction and control

    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
     scorching
    0.53
     температура
    0.46
    ﮧ
    0.46
     பொழுது
    0.45
     поч
    0.44
    avaliacao
    0.44
     imidazol
    0.43
    lığını
    0.43
     ним
    0.43
    َيْ
    0.43
    POSITIVE LOGITS
     }.
    0.50
    Author
    0.48
    জ
    0.48
    LS
    0.47
    াবেক
    0.46
    ফ
    0.45
    Cols
    0.45
    जत
    0.44
    లూ
    0.44
     Anpass
    0.44
    Activations Density 0.001%

    No Known Activations