© 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. 130606
    Prev
    Next
    INDEX
    Explanations

    treaties

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

    building, shrunk, GPT

    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
     ttk
    0.47
    textcolor
    0.46
    cwnd
    0.43
    ibuya
    0.42
    䡃
    0.42
    whole
    0.42
     psor
    0.42
    lees
    0.42
     exchanger
    0.41
    ल्ज
    0.41
    POSITIVE LOGITS
     à
    0.55
    .".
    0.49
    ا
    0.49
    ا۔
    0.47
    .
    0.46
    ".
    0.46
     américain
    0.45
     svě
    0.45
     ».
    0.44
     exemplaire
    0.44
    Activations Density 0.002%

    No Known Activations