© 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. 5498
    Prev
    Next
    INDEX
    Explanations

    Man Sexy

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

    vibe check

    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
    \%).
    0.33
     moteur
    0.31
     glycoproteins
    0.31
     analges
    0.30
     parenteral
    0.30
    लीकरण
    0.29
     oligonucle
    0.29
     malignancies
    0.29
     obsol
    0.29
     oligonucleotide
    0.29
    POSITIVE LOGITS
    ፣
    0.48
    ،
    0.47
    ၊
    0.41
    、
    0.40
    ‬
    0.39
    ؛
    0.38
    ⁩
    0.37
    ">
    0.36
     มี
    0.36
    ,
    0.35
    Activations Density 0.206%

    No Known Activations