© 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. 32856
    Prev
    Next
    INDEX
    Explanations

    treatment

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

    existed anterior land

    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
    ERV
    0.49
    ဝန်
    0.46
     уче
    0.46
    minister
    0.45
    diagram
    0.44
     cadre
    0.44
    沦
    0.44
    VN
    0.43
     அங்கு
    0.43
    Ę
    0.43
    POSITIVE LOGITS
    రుగులు
    0.52
     TREATMENT
    0.43
     oa
    0.42
     Treatment
    0.42
     કરતી
    0.42
     bikini
    0.41
     lp
    0.41
     హీరోయి
    0.41
    amette
    0.41
     Cream
    0.41
    Activations Density 0.000%

    No Known Activations