© 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. 37159
    Prev
    Next
    INDEX
    Explanations

    recipe looks, meet thousands

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

    believe us, competition, latest minor, common words

    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
     خطاب
    0.58
    éndose
    0.46
    ⨔
    0.44
     ထ
    0.43
    কাত
    0.42
    ᆻ
    0.42
    ≜
    0.41
    优先
    0.41
     месту
    0.41
     సందర్భ
    0.40
    POSITIVE LOGITS
     cousins
    0.43
     AISI
    0.43
     ALL
    0.43
    x
    0.42
    ANY
    0.41
    };\
    0.41
     editors
    0.41
     அமைப்பு
    0.41
    umet
    0.41
     ayn
    0.41
    Activations Density 0.000%

    No Known Activations