© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5815
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    accessdate
    0.34
    ucci
    0.31
     and
    0.31
    </h2>
    0.30
    ight
    0.30
    v
    0.29
     apres
    0.28
    前記
    0.27
     apothecary
    0.27
    <0x0D>
    0.27
    POSITIVE LOGITS
     decenas
    0.36
    数百
    0.34
     दस
    0.33
     万元
    0.33
    [multimodal]
    0.33
     ১০
    0.32
    ాత్ర
    0.32
     हजारों
    0.32
    ૩
    0.32
     difficultés
    0.32
    Activations Density 0.095%

    No Known Activations