© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 42989
    Prev
    Next
    INDEX
    Explanations

    vanilla World, a few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )];
    0.54
    ul
    0.50
    ths
    0.48
    ushing
    0.48
    theless
    0.46
    quiet
    0.46
    ounsel
    0.46
    anan
    0.45
    сный
    0.45
    punctuation
    0.45
    POSITIVE LOGITS
     betrokken
    0.58
    <0x80>
    0.56
     artik
    0.52
    เปิด
    0.52
     HMAC
    0.52
     taver
    0.49
     KPIs
    0.49
     exercices
    0.49
    ي
    0.49
     are
    0.48
    Activations Density 0.000%

    No Known Activations