© 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. 31812
    Prev
    Next
    INDEX
    Explanations

    2048 tokens

    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
    وبت
    0.50
    Si
    0.48
    Oc
    0.48
    ይ
    0.48
    I
    0.48
    טים
    0.44
    ት
    0.42
    顷
    0.39
    לק
    0.39
    Aff
    0.38
    POSITIVE LOGITS
    omal
    0.44
    her
    0.43
    ributor
    0.42
    ształ
    0.42
     κι
    0.42
    uem
    0.42
     asli
    0.42
    stainless
    0.42
     portland
    0.42
    ardier
    0.41
    Activations Density 0.016%

    No Known Activations