© 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. 16-GEMMASCOPE-2-RES-262K
    4. 20069
    Prev
    Next
    INDEX
    Explanations

    franchise

    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_16_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
     શરીર
    0.64
     seulement
    0.62
     factual
    0.62
     केवळ
    0.61
     ಪ್ರದೇಶ
    0.61
     făcut
    0.60
     %).
    0.60
     நைட்
    0.60
     କ
    0.60
    単
    0.59
    POSITIVE LOGITS
    ח
    0.69
    س
    0.59
    ף
    0.59
     Diskussion
    0.58
     TextInput
    0.56
    Vendo
    0.56
    r
    0.56
     fila
    0.55
    Munic
    0.55
    Brother
    0.55
    Activations Density 0.001%

    No Known Activations