© 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. 79980
    Prev
    Next
    INDEX
    Explanations

    achieved through, demand, coke bottle, foot in, target research

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

    explaining actions or values

    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
    infection
    0.52
    raient
    0.51
    suivant
    0.47
     ચ
    0.46
    launcher
    0.46
    improvement
    0.46
    ins
    0.46
    Streak
    0.46
    INION
    0.46
    ጣት
    0.46
    POSITIVE LOGITS
     Translated
    0.47
     kos
    0.47
     Hermitian
    0.46
     eigenstates
    0.42
     idiom
    0.42
    陽
    0.41
     Kos
    0.40
     definisi
    0.40
    繇
    0.39
     Matrix
    0.39
    Activations Density 0.000%

    No Known Activations