© 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. 91315
    Prev
    Next
    INDEX
    Explanations

    translates to

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

    detecting redundancy and repetition

    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
     dog
    0.44
    Turner
    0.44
     grape
    0.43
    摄
    0.43
    of
    0.42
     be
    0.41
    Ur
    0.41
    [])
    0.41
     secret
    0.40
    Gra
    0.40
    POSITIVE LOGITS
    ewana
    0.55
     சீனாவின்
    0.54
    aniyam
    0.53
     売場面積
    0.52
     anisot
    0.51
    ektir
    0.50
    কবি
    0.50
    νοντας
    0.50
     politische
    0.50
    hanti
    0.50
    Activations Density 0.000%

    No Known Activations