© 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. 62740
    Prev
    Next
    INDEX
    Explanations

    introduces explanation of capabilities

    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
    ה
    0.55
     arrondi
    0.53
     آش
    0.53
     glomerular
    0.52
     arrondies
    0.52
     viêm
    0.51
     مفت
    0.50
     annealing
    0.50
     fdPar
    0.50
     ovip
    0.49
    POSITIVE LOGITS
    Objects
    0.57
    "-
    0.55
    Object
    0.54
    -
    0.51
    ier
    0.51
    ia
    0.49
    If
    0.48
    objects
    0.47
    ar
    0.47
    ab
    0.46
    Activations Density 0.007%

    No Known Activations