© 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. 74154
    Prev
    Next
    INDEX
    Explanations

    emoticons like :D or :3

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

    UwU speak and emoticons

    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
    ين
    0.59
     ويمكن
    0.57
    }.
    0.53
    шения
    0.53
    에서도
    0.52
    smittel
    0.52
     이제
    0.52
     Lembrando
    0.52
     但是
    0.51
     ؟
    0.51
    POSITIVE LOGITS
    i
    0.63
    ቐ
    0.52
     motherboard
    0.49
     nifty
    0.47
     cationic
    0.46
     x
    0.45
     affirmat
    0.45
     realtor
    0.45
     fractional
    0.44
     bevel
    0.44
    Activations Density 0.001%

    No Known Activations