© 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. 44224
    Prev
    Next
    INDEX
    Explanations

    promise to extent the

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

    believe in, grew, learn

    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
    ulan
    0.46
    Ц
    0.45
    JET
    0.42
    ul
    0.41
    ের
    0.41
    CANADA
    0.41
    லாமல்
    0.40
    Ю
    0.40
     starke
    0.40
    डेजा
    0.39
    POSITIVE LOGITS
    ourcing
    0.41
     ફ
    0.40
     usages
    0.40
     பெருமா
    0.39
    vscode
    0.39
     bison
    0.38
     آباد
    0.38
     ആശ
    0.38
     wybra
    0.38
    币
    0.38
    Activations Density 0.000%

    No Known Activations