© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    error handling or exceptions

    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
    므
    1.07
     furthermore
    0.97
     respectively
    0.96
     hence
    0.93
    ↵
    0.92
     both
    0.89
    }\}$
    0.89
     together
    0.88
     commended
    0.86
    驳
    0.86
    POSITIVE LOGITS
    Pause
    1.31
     adulto
    1.21
     Нет
    1.20
    Existence
    1.19
    Volatility
    1.19
    íš
    1.18
     ocas
    1.18
    Ongoing
    1.14
    Milliseconds
    1.14
    Maybe
    1.13
    Activations Density 0.091%

    No Known Activations