© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5769
    Prev
    Next
    INDEX
    Explanations

    conversational intros and greetings

    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
     mq
    0.33
     tangente
    0.32
    逶
    0.32
     clarifications
    0.31
     paramet
    0.31
     macros
    0.31
     svar
    0.31
     css
    0.30
     protocol
    0.30
     neb
    0.30
    POSITIVE LOGITS
     ♪
    0.47
    ♪
    0.44
    Okay
    0.38
    Speaker
    0.38
    uh
    0.38
     uh
    0.34
    Hey
    0.34
    speaker
    0.34
    Yeah
    0.33
    Hi
    0.33
    Activations Density 0.005%

    No Known Activations