© 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. 160596
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and descriptive items

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

    dual-edged sword: internet, darknets, economy

    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
    (),
    0.45
    Кра
    0.44
    "};
    0.43
    hlt
    0.43
    衅
    0.42
            
    0.41
     guste
    0.41
    (`
    0.41
    (--
    0.39
    ("--------
    0.39
    POSITIVE LOGITS
     ග
    0.53
    یشه
    0.51
    bagi
    0.47
     servici
    0.47
     ऑफ
    0.46
     Mew
    0.46
     इंग्लंड
    0.46
    ᱒
    0.46
    delayed
    0.45
    trav
    0.45
    Activations Density 0.001%

    No Known Activations