© 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. 196555
    Prev
    Next
    INDEX
    Explanations

    financial burdens or costs

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

    sexual acts with animals

    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
    继
    0.47
    为主
    0.47
    Attendees
    0.46
     便
    0.45
     extraordinaire
    0.44
    便
    0.44
    偿
    0.43
    Bearing
    0.42
    ύν
    0.42
    美国
    0.42
    POSITIVE LOGITS
     例えば
    0.52
     जिनको
    0.51
     disrespectful
    0.49
     retorted
    0.49
    :@"
    0.48
     precedenti
    0.47
    .):
    0.46
    dplyr
    0.46
     мои
    0.46
     नीचे
    0.46
    Activations Density 0.002%

    No Known Activations