© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6541
    Prev
    Next
    INDEX
    Explanations

    speaker labels and dialogue

    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_40_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
    =`
    0.40
     வித
    0.40
    ';"
    0.39
     ";"
    0.39
    ,“
    0.39
     นอน
    0.38
    =""
    0.38
     أقل
    0.37
    ='"
    0.37
    '`--
    0.36
    POSITIVE LOGITS
     speaker
    0.50
     Speaker
    0.49
    speaker
    0.48
    Speaker
    0.44
     interviewer
    0.42
     narrator
    0.41
    MR
    0.40
     MR
    0.38
     silence
    0.38
    PP
    0.38
    Activations Density 0.014%

    No Known Activations