© 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. 169004
    Prev
    Next
    INDEX
    Explanations

    money saving practices

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

    character stats

    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
    I
    0.59
    Timelapse
    0.55
    Alchemy
    0.50
    Imagery
    0.49
    Mills
    0.49
    தான்
    0.47
    IMO
    0.46
    sentiment
    0.46
    Xinhua
    0.46
    illumin
    0.45
    POSITIVE LOGITS
     karte
    0.60
     沒有
    0.56
     宝宝
    0.53
     對
    0.50
     počet
    0.49
     苏
    0.49
     skr
    0.49
     goomba
    0.49
     चुनें
    0.49
     Ори
    0.49
    Activations Density 0.000%

    No Known Activations