© 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. 120451
    Prev
    Next
    INDEX
    Explanations

    university, college, institutional

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

    kotlin configuration files

    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
    খাল
    0.45
     lluvias
    0.44
    勮
    0.44
    सलमान
    0.42
     directories
    0.42
    »).
    0.41
     ').
    0.41
    িয়ায়
    0.41
    ુંદર
    0.41
    ானி
    0.41
    POSITIVE LOGITS
    1
    0.56
     대학
    0.46
     Comisión
    0.46
     বিশ্ববিদ্যালয়
    0.45
     UConn
    0.45
     university
    0.45
    CI
    0.45
     في
    0.45
     والإ
    0.44
    adder
    0.43
    Activations Density 0.000%

    No Known Activations