© 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. 251996
    Prev
    Next
    INDEX
    Explanations

    manual activation or state

    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
     سسٹم
    0.49
    starttime
    0.48
    ებისთვის
    0.47
     চৈতন্ত
    0.47
    煂
    0.45
    ributed
    0.45
    گذاری
    0.45
    Portada
    0.44
     شکست
    0.43
    ayısıyla
    0.43
    POSITIVE LOGITS
     twenty
    0.44
     youth
    0.43
     solicitors
    0.42
     literate
    0.41
    颐
    0.41
     heredit
    0.41
    _
    0.41
     руб
    0.41
     creditor
    0.41
     gifting
    0.41
    Activations Density 0.000%

    No Known Activations