© 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. 11730
    Prev
    Next
    INDEX
    Explanations

    potential negative outcomes

    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
     convexes
    0.50
    ricult
    0.46
    segaretro
    0.46
    overnment
    0.45
    欳
    0.44
    qdm
    0.44
     anormal
    0.44
     `>=`,
    0.43
     евре
    0.43
     поколения
    0.42
    POSITIVE LOGITS
    0.55
     I
    0.42
     Adoption
    0.41
     Take
    0.40
     Taking
    0.39
     Dopo
    0.39
     showcase
    0.39
     Zoe
    0.39
     Day
    0.39
     pre
    0.38
    Activations Density 0.001%

    No Known Activations