© 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. 1908
    Prev
    Next
    INDEX
    Explanations

    reporting, growth, needs

    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
     seeming
    0.43
     byla
    0.42
     YOUR
    0.39
     seemed
    0.38
    ग्गा
    0.37
     confine
    0.37
    죤
    0.36
     reportedly
    0.35
     laboratories
    0.35
     була
    0.35
    POSITIVE LOGITS
     sostenibilidad
    0.46
    🫶
    0.44
    🫠
    0.41
    加えて
    0.41
    ₄
    0.41
     hotspots
    0.40
     проє
    0.39
    🥹
    0.39
    🫂
    0.39
     ৭৫
    0.39
    Activations Density 0.030%

    No Known Activations