© 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-65K
    7. 881
    Prev
    Next
    INDEX
    Explanations

    Crisis Text Line 741741

    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_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
    𒁲
    0.34
    ړو
    0.31
     ступен
    0.30
     riego
    0.29
     সবই
    0.29
    شفى
    0.29
     niệm
    0.29
     değerli
    0.29
    વાહી
    0.29
     perfección
    0.29
    POSITIVE LOGITS
     several
    0.33
     his
    0.28
     United
    0.27
     our
    0.27
    www
    0.27
    ↵
    0.26
     https
    0.26
    mates
    0.26
    사에
    0.26
    I
    0.26
    Activations Density 0.064%

    No Known Activations