© 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. 131454
    Prev
    Next
    INDEX
    Explanations

    following words after specific tokens

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

    story begins with one

    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
    cross
    0.49
    Ре
    0.49
    Ис
    0.48
    <td>
    0.48
    Serial
    0.48
    infix
    0.48
    ਪ
    0.48
    Roots
    0.47
    まで
    0.47
    രുദ്ധ
    0.47
    POSITIVE LOGITS
     கிழக்கு
    0.46
     tộc
    0.45
     机
    0.44
     दोन
    0.43
     золото
    0.43
    వంత
    0.43
    दायी
    0.42
     赵
    0.42
    ómico
    0.42
     वन्य
    0.42
    Activations Density 0.000%

    No Known Activations