© 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-16K
    7. 115
    Prev
    Next
    INDEX
    Explanations

    has been

    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_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
    l
    2.31
    r
    2.06
    ка
    1.85
    ان
    1.78
    s
    1.74
    w
    1.74
    ل
    1.71
    t
    1.70
    u
    1.63
    y
    1.57
    POSITIVE LOGITS
     been
    1.97
     gotta
    1.60
    been
    1.52
     BEEN
    1.43
     Been
    1.38
     got
    1.28
     जरिए
    1.20
    queous
    1.14
     flaming
    1.13
     quadrupole
    1.12
    Activations Density 1.098%

    No Known Activations