© 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-65K
    7. 7210
    Prev
    Next
    INDEX
    Explanations

    antihypertensive effect, employees, changes

    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
     والم
    0.36
    پیگنڈ
    0.35
     pomoći
    0.34
     pokud
    0.33
     nouveaux
    0.33
     izan
    0.32
     vetor
    0.32
    ٹ
    0.32
     helpen
    0.31
     saisir
    0.31
    POSITIVE LOGITS
    iton
    0.32
     ассорти
    0.31
    one
    0.31
    hydrocèle
    0.30
     പ്രധാന
    0.30
    from
    0.30
    ont
    0.29
    aldehyde
    0.29
    two
    0.28
    name
    0.28
    Activations Density 0.254%

    No Known Activations