© 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. 106042
    Prev
    Next
    INDEX
    Explanations

    properties and features descriptions

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

    specialized terms or knowledge

    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
    Us
    0.53
    Aplic
    0.51
    Meu
    0.49
     След
    0.47
    Distance
    0.46
     Стра
    0.46
    ඉ
    0.46
    Una
    0.45
    Con
    0.45
    Fin
    0.45
    POSITIVE LOGITS
     accommodates
    0.48
    olecules
    0.47
     раху
    0.47
    ἃ
    0.46
     salesmen
    0.44
     roche
    0.43
    าะ
    0.42
     subdir
    0.42
     interni
    0.42
     quelquefois
    0.42
    Activations Density 0.000%

    No Known Activations