© 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. 110740
    Prev
    Next
    INDEX
    Explanations

    entry point

    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
    ญ
    0.49
     උ
    0.45
     ނ
    0.41
     ಸ್ಥ
    0.40
     teren
    0.40
     ਉ
    0.39
    Surname
    0.39
     piso
    0.39
    éges
    0.39
    ЕЛ
    0.38
    POSITIVE LOGITS
     入
    0.52
     point
    0.46
    入
    0.42
     entrance
    0.41
    きっかけ
    0.40
     Dependent
    0.40
     dependent
    0.38
    portal
    0.38
    point
    0.38
    入り
    0.38
    Activations Density 0.001%

    No Known Activations