© 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. 201927
    Prev
    Next
    INDEX
    Explanations

    signalling that, Nothing contained, know when, bear mining, splitting hairs, enhance your, image content

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

    places and actions described

    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
    ש
    0.51
    Slot
    0.46
    ű
    0.46
    ítás
    0.45
    cha
    0.44
    ish
    0.44
     mogul
    0.42
    č
    0.42
     فِي
    0.42
    א
    0.41
    POSITIVE LOGITS
     Новый
    0.56
     دنی
    0.53
     Importantly
    0.51
     جدید
    0.49
     bahawa
    0.49
     Texte
    0.49
     لوی
    0.49
     اهمیت
    0.49
     głównie
    0.48
    که
    0.48
    Activations Density 0.000%

    No Known Activations