© 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. 184697
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or nouns

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

    `l` flag and specific words

    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
     місто
    0.53
     saco
    0.46
    ﻄ
    0.46
     şehir
    0.45
    levision
    0.44
     фон
    0.44
    factorial
    0.44
    life
    0.43
    ườ
    0.42
    forderung
    0.42
    POSITIVE LOGITS
    ታ
    0.49
    }"/>
    0.46
     Lohia
    0.45
    គ្ន
    0.44
    ब्स
    0.44
     Также
    0.43
    +'
    0.42
    Inher
    0.42
    }">
    0.42
    通过
    0.42
    Activations Density 0.000%

    No Known Activations