© 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. 128039
    Prev
    Next
    INDEX
    Explanations

    this article or posting

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

    debating grappling section area

    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
    ̢
    0.46
     BASIS
    0.45
     HAC
    0.44
     KLM
    0.44
     ODM
    0.43
     szolgált
    0.43
    }_{
    0.43
     duniya
    0.43
    mento
    0.42
    ">⁢</
    0.42
    POSITIVE LOGITS
    obacterial
    0.43
    衾
    0.41
     theological
    0.40
    上也
    0.40
     pronouns
    0.38
     bibliographic
    0.38
     inconclusive
    0.38
    editorial
    0.38
    ᅧ
    0.38
    compensated
    0.37
    Activations Density 0.000%

    No Known Activations