© 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. 181234
    Prev
    Next
    INDEX
    Explanations

    common connecting phrases

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

    old man: weathered

    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
    🕋
    0.54
     Тен
    0.54
     ისინი
    0.53
     აღ
    0.52
     ಸೇ
    0.52
     удовле
    0.51
     энерги
    0.51
     رحمت
    0.50
     Ст
    0.49
     энергия
    0.49
    POSITIVE LOGITS
    1
    0.51
    すると
    0.46
    鉞
    0.46
    بی
    0.45
    แบบ
    0.43
    bi
    0.42
    μα
    0.42
    ገባ
    0.42
    ար
    0.41
    One
    0.41
    Activations Density 0.001%

    No Known Activations