© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7495
    Prev
    Next
    INDEX
    Explanations

    German names

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematics and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ார்
    0.55
     Unidas
    0.52
     розо
    0.51
    辏
    0.50
     έτσι
    0.50
    뛰
    0.49
     artific
    0.48
    㶪
    0.48
     प्रमो
    0.48
     Podczas
    0.48
    POSITIVE LOGITS
    _
    0.52
    >
    0.44
    />
    0.44
    EY
    0.43
    CTION
    0.43
    }}+\
    0.42
    )=>
    0.42
    وْ
    0.41
    EV
    0.41
    '=>$
    0.41
    Activations Density 0.000%

    No Known Activations