© 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. 40-GEMMASCOPE-2-RES-262K
    7. 192673
    Prev
    Next
    INDEX
    Explanations

    instructional computer terms

    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_40_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
    句
    0.42
     put
    0.41
    כ
    0.40
     vap
    0.40
     colour
    0.38
     groin
    0.37
     ruffled
    0.37
     readout
    0.37
     ir
    0.37
     crease
    0.37
    POSITIVE LOGITS
     येणार
    0.39
    Roxy
    0.39
     superClass
    0.38
    റ്റു
    0.37
     जाणार
    0.37
     pageSize
    0.37
     যাইত
    0.37
    ཝ
    0.37
    énés
    0.37
     Avery
    0.37
    Activations Density 0.001%

    No Known Activations