© 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. 162808
    Prev
    Next
    INDEX
    Explanations

    affordable housing and Hufflepuff Sorting

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

    setting up conversations or jokes

    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
     Razer
    0.46
    嗅
    0.44
     hil
    0.44
    police
    0.43
    Police
    0.42
     Luffy
    0.42
    oss
    0.41
     শাস্ত
    0.41
    %
    0.41
     jälkeen
    0.41
    POSITIVE LOGITS
    arının
    0.46
     постро
    0.43
    臤
    0.43
     halfCanvas
    0.43
     भवन
    0.43
     beaming
    0.42
    𝐚
    0.42
    𒊩
    0.42
    原則
    0.42
     wich
    0.42
    Activations Density 0.001%

    No Known Activations