© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 697
    Prev
    Next
    INDEX
    Explanations

    988 Suicide & Crisis Lifeline

    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_65k_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
    oretically
    0.27
     ίδια
    0.25
     implies
    0.25
    ed
    0.25
    istic
    0.24
    <unused2221>
    0.24
     offensively
    0.24
    ously
    0.23
     else
    0.23
    ulent
    0.23
    POSITIVE LOGITS
     T
    0.32
     K
    0.31
     P
    0.31
     M
    0.26
     റ
    0.26
    ಾನೆ
    0.26
     I
    0.25
     കോ
    0.25
    ד
    0.25
     G
    0.25
    Activations Density 0.088%

    No Known Activations