© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136861
    Prev
    Next
    INDEX
    Explanations

    keywords, numbers, objects, URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    𝓹
    0.54
    谜
    0.51
     epistemology
    0.50
    격
    0.50
    홋
    0.50
    ᒧ
    0.50
     یور
    0.49
    ನ್ಯ
    0.46
    ņa
    0.46
    ט
    0.46
    POSITIVE LOGITS
     Tabelle
    0.46
    ains
    0.43
     drows
    0.42
     食
    0.41
    {\
    0.41
    ube
    0.40
    atar
    0.40
    itan
    0.40
    {'
    0.39
    \;
    0.38
    Activations Density 0.008%

    No Known Activations