© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82886
    Prev
    Next
    INDEX
    Explanations

    web-based applications and websites

    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
    pInBuffer
    0.47
     memoranda
    0.45
     punctuation
    0.44
     studia
    0.43
    ارين
    0.43
    thebibliography
    0.43
    鄕
    0.42
     transmembrane
    0.42
    ম্ভীর
    0.42
     trigonometric
    0.42
    POSITIVE LOGITS
    ส
    0.48
     ഉത്സ
    0.44
    OP
    0.44
    گ
    0.42
    ময়
    0.42
    铠
    0.42
    }}^
    0.41
    НО
    0.41
     Opie
    0.41
    SSH
    0.40
    Activations Density 0.001%

    No Known Activations