© 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. 133613
    Prev
    Next
    INDEX
    Explanations

    public transportation, share ideas, virus, veto

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

    multivibrator; oscillator

    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
    rewards
    0.51
    nál
    0.50
    sku
    0.50
    માં
    0.49
    vány
    0.48
    xido
    0.48
    stoke
    0.48
    n
    0.48
     સેવા
    0.48
    rust
    0.48
    POSITIVE LOGITS
    ”:
    0.57
    ":
    0.53
    ”,
    0.52
     lasts
    0.49
    !”
    0.49
     disgusted
    0.48
    !"
    0.48
     are
    0.48
     lob
    0.48
     cerebr
    0.48
    Activations Density 0.000%

    No Known Activations