© 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. 162627
    Prev
    Next
    INDEX
    Explanations

    Haas deal

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

    doing the right thing

    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
    }
    0.51
    άν
    0.44
    ំ
    0.44
     الكلام
    0.44
     thema
    0.43
     كانوا
    0.43
     प्रतिशत
    0.42
     porcent
    0.42
     venen
    0.42
     कंट
    0.42
    POSITIVE LOGITS
    েস্ক
    0.52
    ല
    0.47
     moths
    0.47
    ด
    0.46
    Bsky
    0.46
     juggle
    0.46
    llabus
    0.44
    opf
    0.44
    EEP
    0.43
    𝚕
    0.43
    Activations Density 0.001%

    No Known Activations