© 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. 80710
    Prev
    Next
    INDEX
    Explanations

    underestimated until

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

    etymology and algorithms

    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
    AC
    0.46
     wits
    0.46
    А
    0.46
    充実
    0.45
    IP
    0.45
    К
    0.44
     accept
    0.43
     fyz
    0.43
    CC
    0.43
    М
    0.43
    POSITIVE LOGITS
    róleo
    0.58
    öffnung
    0.57
    ewöhn
    0.57
    chyné
    0.54
    än
    0.54
    ška
    0.54
    äude
    0.53
    AboutDlg
    0.52
    nički
    0.52
    še
    0.51
    Activations Density 0.000%

    No Known Activations