© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9464
    Prev
    Next
    INDEX
    Explanations

    offering further actions or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    1.01
     Архиви
    1.01
     putem
    0.99
     ш
    0.94
     ठीक
    0.94
     опро
    0.94
    𝚍
    0.94
     ре
    0.93
    ごと
    0.92
    명
    0.92
    POSITIVE LOGITS
    वेळी
    1.36
    ocentric
    1.20
    нице
    1.16
     तहत
    1.16
    ﭥ
    1.15
    omania
    1.13
    ｮ
    1.12
    šení
    1.11
    ⿷
    1.11
    ן
    1.11
    Activations Density 0.141%

    No Known Activations