© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 988
    Prev
    Next
    INDEX
    Explanations

    def new / void main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    1
    1.47
    7
    1.47
    3
    1.43
    4
    1.43
    2
    1.38
    5
    1.35
    8
    1.32
    6
    1.30
    9
    1.26
    port
    1.25
    POSITIVE LOGITS
    지
    1.28
    쐞
    1.20
    ה
    1.16
    ಯ
    1.16
    ર
    1.15
     mennesker
    1.08
     жүктөө
    1.08
    εν
    1.05
    𝐨
    1.05
    ﺴ
    1.04
    Activations Density 0.117%

    No Known Activations