© 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. 48808
    Prev
    Next
    INDEX
    Explanations

    and easily, non-invasive, the sample, property, future needs, self-direction, according to

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

    limited range, potential return

    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
    Ps
    0.45
    Zs
    0.45
    起始
    0.44
    Send
    0.44
     cursorPos
    0.43
    Prof
    0.43
    sending
    0.42
    현
    0.42
    援
    0.42
    Arg
    0.41
    POSITIVE LOGITS
     රස
    0.56
     malaysia
    0.52
     Bistro
    0.49
     తిన
    0.49
     വഴി
    0.48
     něco
    0.48
     ricotta
    0.47
     తాగ
    0.47
     Laundry
    0.46
     nostalgic
    0.46
    Activations Density 0.000%

    No Known Activations