© 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. 173521
    Prev
    Next
    INDEX
    Explanations

    without warning

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

    gradual change or phobias

    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
    림
    0.55
    在
    0.54
     சிதம்ப
    0.52
    드
    0.50
    电子
    0.50
    은
    0.49
    끔
    0.49
    산
    0.48
    는
    0.47
    수
    0.46
    POSITIVE LOGITS
    á
    0.50
     vững
    0.46
     SCO
    0.45
     pah
    0.44
     bem
    0.43
    விட்ட
    0.43
    AY
    0.43
     raging
    0.43
     पड़ा
    0.42
     Sampling
    0.42
    Activations Density 0.001%

    No Known Activations