© 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-3-270M-IT
    3. 15-GEMMASCOPE-2-RES-262K
    4. 69631
    Prev
    Next
    INDEX
    Explanations

    e, iloc, електро

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     Subst
    1.45
     isa
    1.30
    गराज
    1.28
    竴
    1.24
     magnolia
    1.20
     btn
    1.19
     CATEG
    1.18
    嘛
    1.17
     subst
    1.17
     Stip
    1.16
    POSITIVE LOGITS
    kal
    1.36
    akos
    1.33
    thoughts
    1.27
    appan
    1.27
    ppro
    1.25
    apanicolaou
    1.24
    body
    1.23
    ë
    1.23
    irond
    1.22
     langchain
    1.21
    Activations Density 0.000%

    No Known Activations