© 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. 88824
    Prev
    Next
    INDEX
    Explanations

    numbers followed by hundred

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

    self vs other experience

    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
     tones
    0.46
    8
    0.44
    );
    0.42
    TWO
    0.42
    ERROR
    0.41
    duh
    0.41
     arid
    0.41
     ,
    0.41
     groupings
    0.41
    href
    0.40
    POSITIVE LOGITS
    鲨
    0.49
     设备
    0.47
    葆
    0.45
     Adviser
    0.44
     मैती
    0.44
     ఇటీవల
    0.43
     బ్యాం
    0.43
     상담
    0.43
    stown
    0.43
    ပိုင်း
    0.43
    Activations Density 0.000%

    No Known Activations