© 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. 97567
    Prev
    Next
    INDEX
    Explanations

    common phrase completions

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

    advice and contextualizing claims

    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
     년
    0.46
    etically
    0.45
    Rh
    0.45
    stall
    0.45
    streets
    0.45
    Hispanic
    0.44
    atsioon
    0.44
    nights
    0.44
    akum
    0.44
    literature
    0.43
    POSITIVE LOGITS
     فوتبال
    0.51
     пациен
    0.49
     прозра
    0.46
    ＝
    0.46
     последствия
    0.45
     فوتب
    0.44
     предстоя
    0.43
    =.
    0.43
    䒱
    0.43
    κά
    0.43
    Activations Density 0.000%

    No Known Activations