© 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. 75
    Prev
    Next
    INDEX
    Explanations

    highly realistic speech

    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
     ettha
    0.55
     Ст
    0.52
     Aś
    0.51
     божомол
    0.51
     vitth
    0.50
     Bxb
    0.50
     Bhagava
    0.48
    뜰
    0.48
     ሽፋ
    0.47
    ናል
    0.47
    POSITIVE LOGITS
    ins
    0.52
    ars
    0.52
    ً
    0.51
    versions
    0.48
    eps
    0.48
    arts
    0.46
    َ
    0.46
    enges
    0.45
    affen
    0.44
    ks
    0.44
    Activations Density 0.000%

    No Known Activations