© 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. 6121
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    directional movement or numerical comparisons

    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
    FURNIZOR
    0.47
    GEBURTS
    0.43
    Strafpunkte
    0.43
     Oldborough
    0.43
    𝙠
    0.42
    כּ
    0.42
    DanhMucSP
    0.41
    Disha
    0.41
    castellan
    0.41
     castom
    0.41
    POSITIVE LOGITS
    0.63
     and
    0.55
    1
    0.55
     +
    0.53
    6
    0.52
     C
    0.51
    2
    0.51
     I
    0.49
     M
    0.49
    5
    0.49
    Activations Density 0.008%

    No Known Activations