© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136717
    Prev
    Next
    INDEX
    Explanations

    informative text and reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ight
    0.52
     tweede
    0.50
     podp
    0.46
     beide
    0.46
     Ahab
    0.45
     $\%$
    0.45
     wers
    0.44
     osoby
    0.44
    тный
    0.44
     teknik
    0.44
    POSITIVE LOGITS
     일본
    0.51
    μέ
    0.45
     מק
    0.44
     mourning
    0.44
     배열
    0.44
    ances
    0.43
     ćemo
    0.43
     채팅
    0.43
     اتمنى
    0.43
     Ο
    0.42
    Activations Density 0.001%

    No Known Activations