© 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. 46096
    Prev
    Next
    INDEX
    Explanations

    opt-in and bathroom descriptions

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

    regulatory, claim, API, mail

    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
    擞
    0.43
     indignant
    0.43
    eni
    0.41
    jectives
    0.41
    iveness
    0.41
    不易
    0.41
    }!
    0.40
     disgusted
    0.40
    äns
    0.40
     सामील
    0.40
    POSITIVE LOGITS
    ו
    0.53
     سیستم
    0.52
    Extraction
    0.51
     subprocess
    0.49
     وړ
    0.48
    CTL
    0.48
    システム
    0.47
     Extraction
    0.47
    ΜΑ
    0.47
    קט
    0.47
    Activations Density 0.000%

    No Known Activations