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. 40-GEMMASCOPE-2-RES-262K
    4. 3832
    Prev
    Next
    INDEX
    Explanations

    988 suicide hotline context

    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
    DISABLED
    0.26
    Crossing
    0.25
     ಆತ್ಮ
    0.25
    𝟕
    0.24
     \{\
    0.24
     ٻ
    0.24
    ዎት
    0.24
     ૧
    0.24
    ைகளும்
    0.24
    Fundamental
    0.23
    POSITIVE LOGITS
    ′
    0.55
    ″
    0.52
    th
    0.49
    ths
    0.39
    %
    0.39
    ′,
    0.39
     градусов
    0.37
     series
    0.37
    MHz
    0.37
    GHz
    0.37
    Activations Density 0.142%

    No Known Activations