© 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. 28264
    Prev
    Next
    INDEX
    Explanations

    author names

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

    romance book writing prompts

    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
    bahnhof
    0.46
     dehuman
    0.45
     János
    0.45
     मनोज
    0.44
     প্রতিদিন
    0.42
     Artur
    0.42
     abusers
    0.42
    Ⴊ
    0.42
     स्पोर्ट
    0.41
     Einrichtung
    0.41
    POSITIVE LOGITS
     secretaries
    0.43
    প্র
    0.39
    сл
    0.38
     اتا
    0.38
     applicant
    0.38
    catal
    0.37
    ice
    0.37
    ethoxy
    0.36
    issi
    0.35
     catal
    0.35
    Activations Density 0.000%

    No Known Activations