© 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. 40417
    Prev
    Next
    INDEX
    Explanations

    posted on, in, or by

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

    posting content on dates

    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
    HeightSizeMode
    0.44
     engulfed
    0.41
     Ausstattung
    0.41
    }$)
    0.41
     ಕೂಡ
    0.40
    êté
    0.39
     नक्की
    0.39
    នៃការ
    0.39
     yattha
    0.39
    }^{*}-
    0.38
    POSITIVE LOGITS
     posted
    0.79
    Posted
    0.73
     posting
    0.72
     Posted
    0.70
    posted
    0.63
     post
    0.61
     પોસ્ટ
    0.61
     Posting
    0.61
     repost
    0.59
     postings
    0.57
    Activations Density 0.027%

    No Known Activations