© 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. 12-GEMMASCOPE-2-RES-65K
    4. 1486
    Prev
    Next
    INDEX
    Explanations

    step by step explanations

    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_12_width_65k_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
    荆
    1.24
     Skyrim
    1.18
    '[
    1.18
    เส
    1.18
    ❃
    1.18
    IMENTO
    1.14
    SPIR
    1.13
    IRONMENT
    1.10
     imping
    1.09
     Innsbruck
    1.08
    POSITIVE LOGITS
    力度
    1.15
    けます
    1.14
    ة
    1.11
     calendar
    1.10
     das
    1.08
    经费
    1.07
     dello
    1.07
    uas
    1.07
    uad
    1.06
    数は
    1.06
    Activations Density 0.046%

    No Known Activations