© 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. 221903
    Prev
    Next
    INDEX
    Explanations

    cost-effective and more easy

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

    riddles and descriptive 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
    国防
    0.53
     დაი
    0.48
    兮
    0.48
     ক্ষেপণাস্ত্র
    0.47
    驄
    0.47
     budou
    0.47
     รอ
    0.46
     hoofd
    0.46
    訸
    0.46
     יו
    0.46
    POSITIVE LOGITS
    x
    0.49
    <0xD8>
    0.42
    slot
    0.41
    сү
    0.41
    si
    0.41
    г
    0.40
    Ses
    0.40
     Individ
    0.40
    all
    0.39
    sar
    0.39
    Activations Density 0.000%

    No Known Activations