© 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. 22-GEMMASCOPE-2-RES-65K
    7. 4890
    Prev
    Next
    INDEX
    Explanations

    aftercorrection

    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_22_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
     desafios
    1.36
    ап
    1.15
    ѕ
    1.10
     desafíos
    1.05
     Кня
    1.04
    de
    1.03
     څنګه
    1.03
     grec
    1.01
    Ԁ
    1.01
     slechts
    1.00
    POSITIVE LOGITS
    getAll
    1.09
    sides
    1.08
    apeutic
    1.07
    a
    1.02
    eous
    1.01
     autoradi
    1.00
    ać
    1.00
    opathology
    0.98
     intermolecular
    0.98
    ా
    0.98
    Activations Density 0.000%

    No Known Activations