© 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. 234538
    Prev
    Next
    INDEX
    Explanations

    citations and numbered items

    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
     वजह
    0.55
    原因
    0.47
    Ethics
    0.46
    ↵
    0.46
     mely
    0.46
    Acetic
    0.45
    滴
    0.45
    ᑕ
    0.45
     Acces
    0.45
     Drops
    0.43
    POSITIVE LOGITS
    레이
    0.58
    ต์
    0.47
    erin
    0.46
     레이
    0.45
     एन
    0.44
    um
    0.43
    ыл
    0.42
    색
    0.42
    вый
    0.41
     reload
    0.41
    Activations Density 0.000%

    No Known Activations