© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 3628
    Prev
    Next
    INDEX
    Explanations

    object attribute naming conventions

    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_53_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
    分手
    0.38
    篪
    0.38
     हर्
    0.36
     Ríos
    0.36
     ナイ
    0.35
    ﷲ
    0.34
    醗
    0.34
    ໃຊ້
    0.33
    Gill
    0.33
    onske
    0.33
    POSITIVE LOGITS
    __
    0.40
    _
    0.39
    public
    0.36
    ENUM
    0.36
    AN
    0.35
    JsonProperty
    0.35
    $$_
    0.34
    protocol
    0.34
    typeof
    0.33
    ATION
    0.33
    Activations Density 0.032%

    No Known Activations