© 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. 9670
    Prev
    Next
    INDEX
    Explanations

    acceptable and not worthy

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

    suitable, good, acceptable

    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
     rarement
    0.50
    雙
    0.47
     omnip
    0.46
     డై
    0.45
     khắp
    0.45
     prophylaxis
    0.44
     බොහෝ
    0.44
     pogled
    0.43
     jarang
    0.43
     分
    0.43
    POSITIVE LOGITS
     উপযুক্ত
    0.57
    acceptable
    0.55
    good
    0.55
    suitable
    0.54
     worthy
    0.54
     deserving
    0.53
    有害
    0.52
     deserves
    0.51
     deserve
    0.51
     betterment
    0.50
    Activations Density 0.087%

    No Known Activations