© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8418
    Prev
    Next
    INDEX
    Explanations

    LM Studio

    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_9_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
    𝐢
    3.24
    𝐝
    3.11
    𝐧
    3.07
    𝐩
    2.90
    𝐚
    2.87
    ಯ
    2.81
    YA
    2.75
    า
    2.72
    𝐫
    2.72
    ergy
    2.71
    POSITIVE LOGITS
    ﮧ
    2.79
    zeitig
    2.69
     того
    2.69
    אה
    2.68
    𝚜
    2.63
     CONCLUS
    2.63
    ால்
    2.59
    us
    2.54
     accom
    2.54
     fetching
    2.53
    Activations Density 0.023%

    No Known Activations