© 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. 42051
    Prev
    Next
    INDEX
    Explanations

    adjustments and fitting

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

    Adjust layout

    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
    avacanam
    0.53
     அல்லது
    0.52
    ات
    0.48
    ة
    0.48
    监
    0.45
    繹
    0.44
    َة
    0.44
    ⌬
    0.44
     وم
    0.43
    asına
    0.43
    POSITIVE LOGITS
     disobedience
    0.50
     श्रीदेवी
    0.47
     ReLU
    0.45
     hoodie
    0.44
     shameful
    0.44
     treason
    0.44
     Cinderella
    0.44
     torsional
    0.44
     rebellious
    0.44
     symmetric
    0.44
    Activations Density 0.000%

    No Known Activations