© 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. 33169
    Prev
    Next
    INDEX
    Explanations

    rug cleaning

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

    absence of

    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
     siste
    0.43
     зада
    0.43
    strup
    0.41
    igene
    0.41
    fil
    0.40
    電機
    0.40
     প্রতিটি
    0.39
    答
    0.39
    ptions
    0.39
    隨著
    0.39
    POSITIVE LOGITS
    𝘻
    0.46
     Νο
    0.45
     pomoć
    0.45
    အ
    0.45
     restor
    0.44
     towarz
    0.44
     montana
    0.44
     sheets
    0.43
    lamak
    0.42
    nickname
    0.42
    Activations Density 0.000%

    No Known Activations