© 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. 202012
    Prev
    Next
    INDEX
    Explanations

    legal or compliance terms

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

    bodies of text

    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
    この
    0.50
     ovales
    0.45
     prevailing
    0.44
     evam
    0.43
    ഈ
    0.42
     apex
    0.41
     böl
    0.41
     Acid
    0.41
     perdida
    0.40
     この
    0.40
    POSITIVE LOGITS
    툼
    0.48
     dunno
    0.46
     stateless
    0.46
    ებ
    0.45
     служба
    0.45
    InCM
    0.44
    adás
    0.44
    rotechn
    0.43
     getDate
    0.43
     heresy
    0.43
    Activations Density 0.001%

    No Known Activations