© 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. 60421
    Prev
    Next
    INDEX
    Explanations

    cup of tea

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

    version and artifact details

    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
     direktor
    0.49
    amard
    0.41
     nevo
    0.41
    owymi
    0.41
    }^{*}-
    0.40
     اهم
    0.40
    ቾ
    0.40
    timedelta
    0.39
     pertin
    0.39
     omissions
    0.39
    POSITIVE LOGITS
     we
    0.50
    Allen
    0.45
    龰
    0.45
    Ray
    0.44
    ໍ່
    0.44
    creatic
    0.43
     प्रतिदिन
    0.43
    全年
    0.43
    8
    0.43
     monthly
    0.42
    Activations Density 0.000%

    No Known Activations