© 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. 224099
    Prev
    Next
    INDEX
    Explanations

    pom peter / per person

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

    shown architectural relationships

    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
     машиналарын
    0.49
     поча
    0.47
     preachers
    0.47
    PropertyList
    0.47
    Estados
    0.47
    ต่างๆ
    0.46
    钏
    0.46
     інших
    0.45
     ఉత్ప
    0.44
    meck
    0.44
    POSITIVE LOGITS
     Tom
    0.51
     Góc
    0.45
     Heidi
    0.45
     Khánh
    0.43
    ació
    0.42
    ="#
    0.42
    hão
    0.42
    ေါ်
    0.42
     shadowed
    0.42
     Rio
    0.42
    Activations Density 0.001%

    No Known Activations