© 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. 153603
    Prev
    Next
    INDEX
    Explanations

    school admission, to look

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

    inter-rater reliability

    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
    ্তে
    0.46
    人心
    0.44
     กลับ
    0.42
    ^{(\
    0.41
     Easter
    0.41
    bookings
    0.41
     lL
    0.40
    ispens
    0.40
     hoher
    0.40
    ekwondo
    0.40
    POSITIVE LOGITS
    物的
    0.46
    ガラ
    0.46
    i
    0.44
    inie
    0.44
    nat
    0.44
     hydrate
    0.44
    NotFoundError
    0.44
    ۲
    0.43
    ધાન
    0.43
    ދު
    0.42
    Activations Density 0.000%

    No Known Activations