© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 284
    Prev
    Next
    INDEX
    Explanations

    not safe for work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     This
    1.13
     (
    0.93
     of
    0.92
     این
    0.91
     ل
    0.89
     Whether
    0.84
     If
    0.84
     Despite
    0.81
     with
    0.81
     even
    0.79
    POSITIVE LOGITS
    𒂰
    1.60
    𒌼
    1.60
    𒁠
    1.59
    𒀓
    1.59
    FBSDKMacros
    1.59
    𒀺
    1.59
    𒐶
    1.59
    𒄪
    1.59
    𒀻
    1.59
    𒁌
    1.59
    Activations Density 0.005%

    No Known Activations