© 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. 40-GEMMASCOPE-2-RES-262K
    4. 133928
    Prev
    Next
    INDEX
    Explanations

    Gospel, Leap, Food, citizen

    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_262k_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
    bracelet
    0.45
     handheld
    0.42
     bracelet
    0.41
    acia
    0.41
    液
    0.40
    စွာ
    0.40
    စီ
    0.40
    弹
    0.40
     நிறு
    0.40
    aircraft
    0.40
    POSITIVE LOGITS
     Citizen
    0.49
     Enemy
    0.46
     citizen
    0.45
     metaphys
    0.43
     BASE
    0.43
     ciudadano
    0.43
     Cup
    0.42
     offended
    0.42
     Capacity
    0.41
     Kun
    0.41
    Activations Density 0.005%

    No Known Activations