© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4568
    Prev
    Next
    INDEX
    Explanations

    initiating model responses

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

    the presence of the model/assistant role token that marks the model's generated response.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     faiblement
    0.32
     punctatis
    0.31
    <unused98>
    0.30
     demethyl
    0.29
    زار
    0.29
     unwillingness
    0.28
     cambiamento
    0.28
     pessim
    0.28
    ylobacter
    0.28
     பதில்
    0.27
    POSITIVE LOGITS
    Getting
    0.30
    ↵↵
    0.29
     Get
    0.28
    aming
    0.28
    Be
    0.28
    Luxury
    0.28
    о
    0.28
    Get
    0.27
     luxury
    0.27
     Getting
    0.27
    Activations Density 0.193%

    No Known Activations