© 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. 154600
    Prev
    Next
    INDEX
    Explanations

    tools, points, words, opinion

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

    free tools

    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
    ἃ
    0.58
     Stiftung
    0.53
     alertDialog
    0.52
     SALES
    0.51
    يري
    0.50
    栗
    0.49
    ﻂ
    0.49
     thisTrial
    0.49
    Ⴖ
    0.49
    об
    0.47
    POSITIVE LOGITS
    ement
    0.48
    enn
    0.48
    isolated
    0.48
    ned
    0.47
    kun
    0.47
    itzen
    0.46
    jets
    0.46
    lement
    0.45
    annan
    0.44
    ir
    0.44
    Activations Density 0.001%

    No Known Activations