© 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. 178961
    Prev
    Next
    INDEX
    Explanations

    delivers coming data Webster

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

    prohibitions and added value

    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
    ریم
    0.48
    ICH
    0.45
     Shim
    0.43
    دی
    0.42
    2
    0.42
     EPS
    0.42
    ガ
    0.42
    eli
    0.41
    ང
    0.41
     Committees
    0.41
    POSITIVE LOGITS
     wybra
    0.50
    Etiam
    0.49
     исти
    0.46
     cüm
    0.46
    peuta
    0.46
     UIApplication
    0.45
    륜
    0.45
     realty
    0.45
    lingu
    0.44
    νει
    0.44
    Activations Density 0.000%

    No Known Activations