© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 238
    Prev
    Next
    INDEX
    Explanations

    names and initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     Begriff
    0.35
    것
    0.33
     അമേ
    0.33
     comforting
    0.32
    displaystyle
    0.32
     grandiose
    0.32
     wording
    0.32
     poem
    0.32
     അദ്ദേഹ
    0.32
     poetic
    0.32
    POSITIVE LOGITS
     J
    0.46
     Zhang
    0.46
     S
    0.46
     R
    0.44
     M
    0.44
     Zhao
    0.44
     C
    0.43
    {\'
    0.42
     postdoctoral
    0.41
    ǧ
    0.41
    Activations Density 0.043%

    No Known Activations