© 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. 103996
    Prev
    Next
    INDEX
    Explanations

    mailinglist communications

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

    FreeBSD kernel compatibility

    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
    khidmat
    0.44
    ボリー
    0.43
    Asie
    0.42
     Selamat
    0.42
     Sabha
    0.41
    Сред
    0.41
    쁩
    0.40
    쁨
    0.40
    aecat
    0.40
    ࿔
    0.40
    POSITIVE LOGITS
     plast
    0.53
     vowel
    0.48
     phon
    0.46
     penal
    0.46
     Phon
    0.45
     dioxygen
    0.44
     diast
    0.44
     sp
    0.43
     æ
    0.43
     antifer
    0.42
    Activations Density 0.001%

    No Known Activations