© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77725
    Prev
    Next
    INDEX
    Explanations

    actions followed by results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ོན་
    0.50
     likewise
    0.46
     किश
    0.46
    ங்கும்
    0.46
    leqq
    0.46
    ましたが
    0.46
    軻
    0.46
     incorpora
    0.45
     reactionary
    0.45
    역
    0.44
    POSITIVE LOGITS
    stä
    0.49
     původ
    0.49
    avad
    0.45
    alom
    0.45
    Alam
    0.44
     Glad
    0.43
     digs
    0.43
     Alameda
    0.42
     Amal
    0.42
     Aug
    0.42
    Activations Density 0.001%

    No Known Activations