© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38137
    Prev
    Next
    INDEX
    Explanations

    arrest, rickets, ID, frittata

    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_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
    的很
    1.57
     excision
    1.55
     irradiance
    1.49
    CHREIBUNG
    1.46
    エース
    1.46
    ⟋
    1.46
     OSX
    1.44
     inoculum
    1.44
     ayahuasca
    1.43
     hydrox
    1.42
    POSITIVE LOGITS
    ų
    1.46
     a
    1.28
    .
    1.28
    ._
    1.24
            
    1.23
    O
    1.23
     d
    1.21
    ot
    1.20
    ,
    1.17
    었다
    1.14
    Activations Density 0.003%

    No Known Activations