© 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. 122527
    Prev
    Next
    INDEX
    Explanations

    engine output or armoured tank

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

    hydrogen bonds and bottles

    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
     ہندوستان
    0.50
     เหรอ
    0.49
     интервью
    0.45
    correo
    0.45
     メール
    0.44
    별
    0.44
    시대
    0.44
    选取
    0.44
    颏
    0.44
    је
    0.44
    POSITIVE LOGITS
     cabinet
    0.50
     machinery
    0.49
     compressor
    0.47
     TCS
    0.46
     immersion
    0.46
     C
    0.45
     covering
    0.45
     expulsion
    0.45
     accelerator
    0.44
     injections
    0.44
    Activations Density 0.000%

    No Known Activations