© 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-65K
    7. 13954
    Prev
    Next
    INDEX
    Explanations

    conversational transitions and affirmations

    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_65k_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
    :
    0.39
     Scrolling
    0.36
    ’
    0.36
     adalah
    0.35
     είναι
    0.35
     là
    0.34
    '
    0.34
     är
    0.33
     Animation
    0.33
    ,
    0.33
    POSITIVE LOGITS
     ততদিন
    0.33
    䊀
    0.30
    पोरेशन
    0.30
     symmet
    0.29
    ఆర్‌
    0.29
    。<
    0.29
    </thead>
    0.29
    రిగ
    0.29
     precautionary
    0.29
    KLC
    0.29
    Activations Density 0.039%

    No Known Activations