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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 113170
    Prev
    Next
    INDEX
    Explanations

    he seems

    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
    </h3>
    0.52
     Voor
    0.50
    C
    0.49
     Proven
    0.48
     Cer
    0.47
    ),
    0.46
     ,
    0.46
     gle
    0.46
     Kron
    0.45
     Anda
    0.45
    POSITIVE LOGITS
    isTouching
    0.55
    萸
    0.50
    urangan
    0.50
    ajout
    0.50
    젖
    0.49
     자연
    0.48
    stö
    0.48
    하시오
    0.47
    stimulated
    0.47
    metre
    0.47
    Activations Density 0.000%

    No Known Activations