© 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. 105520
    Prev
    Next
    INDEX
    Explanations

    phrases where a word precedes another

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

    counting words and abbreviations

    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
     Baiklah
    0.49
     Neighbour
    0.48
    ụ
    0.46
     Đài
    0.45
    饶
    0.45
     hypothalam
    0.44
     deities
    0.43
     Kuch
    0.43
     Nghi
    0.43
     shelters
    0.42
    POSITIVE LOGITS
    i
    0.63
    friction
    0.59
    innovation
    0.58
    Plan
    0.55
    Learning
    0.53
    Profession
    0.52
    Property
    0.52
    Opportunities
    0.52
    Options
    0.51
    Instant
    0.51
    Activations Density 0.001%

    No Known Activations