© 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. 204426
    Prev
    Next
    INDEX
    Explanations

    carefully selected

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

    descriptive adjacent words

    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
    Ꮏ
    0.50
     stesse
    0.50
    となって
    0.48
     femei
    0.48
    については
    0.48
     tuv
    0.48
     մաս
    0.48
    긍
    0.48
     przedmiot
    0.47
    国際
    0.47
    POSITIVE LOGITS
    oves
    0.46
    ane
    0.44
    heem
    0.44
    dail
    0.44
     Voices
    0.42
    coherent
    0.42
    transitions
    0.41
    vscode
    0.41
    confident
    0.41
    rim
    0.41
    Activations Density 0.000%

    No Known Activations