Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169828
    Prev
    Next
    INDEX
    Explanations

    harmful or prohibited content involving minors

    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
    ม
    0.47
     zählt
    0.47
     zählen
    0.46
    %}
    0.43
     งาน
    0.40
     آم
    0.40
     때문에
    0.40
     môže
    0.40
     такі
    0.40
     тощо
    0.40
    POSITIVE LOGITS
     memeriksa
    0.46
     swoim
    0.45
    闓
    0.45
    CLUDED
    0.45
    כל
    0.44
    検査
    0.43
    едера
    0.43
    deoxy
    0.43
     своим
    0.42
    ρθρο
    0.42
    Activations Density 0.006%

    No Known Activations