© 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. 69210
    Prev
    Next
    INDEX
    Explanations

    educational items and exams

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

    attraction and dynamics

    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
    ’
    0.55
     centroid
    0.55
     affliction
    0.50
     ∀
    0.49
     concatenated
    0.48
    \]
    0.48
     थेट
    0.46
     legitimacy
    0.45
    ロス
    0.45
     ŝ
    0.45
    POSITIVE LOGITS
     arqué
    0.60
    ifiziert
    0.47
     melts
    0.46
     ordre
    0.45
     Europeo
    0.45
    كتب
    0.45
     বিষয়ের
    0.44
    ండ్లు
    0.44
    ılır
    0.44
     送
    0.43
    Activations Density 0.000%

    No Known Activations