© 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. 9512
    Prev
    Next
    INDEX
    Explanations

    legal and ethical information

    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
     défendre
    1.23
     combinations
    1.22
     corrects
    1.20
     swans
    1.16
     slags
    1.13
     Kimura
    1.11
    褰
    1.11
     bromide
    1.10
     overcame
    1.10
     electrophoresis
    1.09
    POSITIVE LOGITS
    я
    1.13
    mun
    1.09
    cies
    1.07
    comput
    1.06
    aat
    1.03
    s
    1.03
    criptions
    1.01
    aic
    1.00
    gewicht
    1.00
    ت
    0.98
    Activations Density 0.004%

    No Known Activations