© 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. 232168
    Prev
    Next
    INDEX
    Explanations

    legal and business terms

    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
    晤
    0.46
    cobra
    0.45
    зву
    0.45
    ясплат
    0.44
     ఉపయోగ
    0.44
     लीजिएगा
    0.43
    嘗試
    0.43
    ͓
    0.43
    峩
    0.43
    着用
    0.42
    POSITIVE LOGITS
    ca
    0.45
     sensed
    0.44
    ből
    0.42
    0
    0.42
    বাসী
    0.42
     Dunes
    0.42
    mma
    0.41
     نبی
    0.41
     Compressed
    0.41
     Calibration
    0.40
    Activations Density 0.002%

    No Known Activations