© 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. 139111
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols

    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
    ริญ
    0.40
    ില
    0.40
    悦
    0.39
     fattori
    0.38
    orld
    0.37
    ेंड
    0.37
    >{
    0.37
    нди
    0.37
    >{{
    0.37
    ”…
    0.37
    POSITIVE LOGITS
    ႇ
    0.54
     abrog
    0.49
     demonic
    0.47
    т
    0.45
    ная
    0.44
    における
    0.42
    逆に
    0.42
     اجمعين
    0.42
    क्टूबर
    0.41
     abducted
    0.41
    Activations Density 0.005%

    No Known Activations