© 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. 3008
    Prev
    Next
    INDEX
    Explanations

    states, processes, or qualities

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

    describing specific qualities or methods

    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
     be
    0.54
     sebagainya
    0.49
    ls
    0.47
     を
    0.47
     entsprechende
    0.46
    penas
    0.44
    bies
    0.42
     entsprechenden
    0.42
     entspre
    0.41
     முற
    0.41
    POSITIVE LOGITS
    :
    0.81
     émotion
    0.53
    श्विक
    0.49
     emozioni
    0.49
    และ
    0.48
    וף
    0.47
    नमस्ते
    0.47
     лично
    0.46
     emocional
    0.46
    น์
    0.46
    Activations Density 0.566%

    No Known Activations