© 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. 65540
    Prev
    Next
    INDEX
    Explanations

    following information

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

    mathematical calculation explanation

    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
     Hints
    0.46
     чтоб
    0.44
    汉语
    0.44
    欲望
    0.42
     ইচ্ছা
    0.42
     темпера
    0.41
     Яро
    0.41
    踩
    0.41
    要因
    0.41
    вна
    0.40
    POSITIVE LOGITS
     following
    0.56
     følgende
    0.52
     three
    0.51
     seguinte
    0.46
     seguito
    0.46
     निम्नलिखित
    0.46
     follows
    0.46
     Following
    0.45
    Following
    0.45
     다음과
    0.45
    Activations Density 0.003%

    No Known Activations