© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52941
    Prev
    Next
    INDEX
    Explanations

    overlapping or blocking

    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_31_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
    只有
    0.46
    diameter
    0.44
     presupuesto
    0.41
    づくり
    0.41
    압
    0.40
    う
    0.40
    用
    0.40
    창
    0.39
    ۸
    0.39
     ovaj
    0.39
    POSITIVE LOGITS
     deny
    0.47
     minimise
    0.46
     arrive
    0.45
     postpone
    0.44
     denies
    0.44
     browse
    0.43
     enrich
    0.42
     remain
    0.42
     succeed
    0.42
     evade
    0.41
    Activations Density 0.000%

    No Known Activations