© 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. 36777
    Prev
    Next
    INDEX
    Explanations

    wanting and dissatisfaction

    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
    ಷ್ಣ
    0.40
     Jahrhundert
    0.36
     mennes
    0.36
     mimicking
    0.36
     puoi
    0.36
    譴
    0.36
     internacionales
    0.36
    ವೇಂದ್ರ
    0.36
    報告
    0.35
    ">{
    0.35
    POSITIVE LOGITS
     miała
    0.47
     receive
    0.46
    ាន
    0.45
    łącznie
    0.44
     geld
    0.43
     terl
    0.43
     получа
    0.43
     domine
    0.43
     गाडी
    0.42
     fla
    0.42
    Activations Density 0.015%

    No Known Activations