© 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-65K
    7. 14640
    Prev
    Next
    INDEX
    Explanations

    past and present states

    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_65k_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
    නී
    0.42
     Pří
    0.41
    浼
    0.41
     threat
    0.40
     eventuali
    0.40
     theologian
    0.40
    ێ
    0.40
     alkal
    0.39
     kó
    0.39
     Europese
    0.39
    POSITIVE LOGITS
    ioutil
    0.45
    cut
    0.43
     জায়গা
    0.42
    roi
    0.42
     לו
    0.41
    teau
    0.41
     ຈ
    0.41
     একদম
    0.40
     थक
    0.40
    tbLabel
    0.40
    Activations Density 0.030%

    No Known Activations