© 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. 24-GEMMASCOPE-2-RES-262K
    7. 7604
    Prev
    Next
    INDEX
    Explanations

    processing or manipulating information

    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_24_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
     Funktions
    0.42
     Statement
    0.38
     ModInt
    0.37
    ٠
    0.36
    Humidity
    0.36
    ああ
    0.35
    Statement
    0.35
    َب
    0.34
     Taxonomic
    0.33
    iprofloxacin
    0.33
    POSITIVE LOGITS
     the
    0.47
     or
    0.42
     thei
    0.41
     others
    0.41
     it
    0.41
     their
    0.40
     his
    0.40
     extant
    0.39
     and
    0.38
     things
    0.38
    Activations Density 0.400%

    No Known Activations