© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 97123
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    creative acidity baking soda characters

    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
     horribly
    0.46
    }=\{\
    0.45
     awfully
    0.44
     lifeless
    0.43
    }=\{
    0.42
    псо
    0.42
    =\{\
    0.41
     disperse
    0.41
    }\{\
    0.40
    झ्
    0.40
    POSITIVE LOGITS
     Weitere
    0.49
     nutzen
    0.46
     தங்க
    0.46
     accéder
    0.46
     savoury
    0.45
    කර
    0.45
     Biochemistry
    0.45
    ရန်
    0.45
     achten
    0.44
    kowy
    0.44
    Activations Density 0.000%

    No Known Activations