© 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. 216823
    Prev
    Next
    INDEX
    Explanations

    curse God

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

    query intents and downstream tasks

    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
    혔
    0.48
    不久
    0.47
    reszt
    0.46
    虑
    0.46
    हरादून
    0.44
    的不
    0.44
    幺
    0.43
    廪
    0.42
    స్
    0.41
    不知
    0.40
    POSITIVE LOGITS
    ﻬ
    0.49
     стрем
    0.47
    ﻤ
    0.47
    city
    0.47
     Typhoon
    0.46
    ار
    0.45
     croissant
    0.45
     showcasing
    0.45
     victoria
    0.44
     معامل
    0.44
    Activations Density 0.000%

    No Known Activations