© 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-262K
    7. 25857
    Prev
    Next
    INDEX
    Explanations

    command-line flags

    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_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
    することができる
    0.48
    ることができる
    0.46
     شاف
    0.45
    StillWater
    0.43
    ButtonItem
    0.43
    етесь
    0.43
    ίζεται
    0.42
    釦
    0.42
     በሚ
    0.41
    就可以
    0.41
    POSITIVE LOGITS
    o
    0.48
    use
    0.48
     detachable
    0.44
    E
    0.44
     dry
    0.44
     didn
    0.43
     penuh
    0.43
    olve
    0.43
    se
    0.43
     volg
    0.42
    Activations Density 0.066%

    No Known Activations