© 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. 185971
    Prev
    Next
    INDEX
    Explanations

    place names and specific nouns

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

    credit structure due sauce palindromic

    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
     thefe
    0.48
    ोक
    0.48
     אשר
    0.47
    ⵏ
    0.45
     gloom
    0.45
    
    0.45
     comerciais
    0.45
     імені
    0.44
     aceste
    0.44
     রোধ
    0.42
    POSITIVE LOGITS
    뿜
    0.48
    czak
    0.45
    fted
    0.42
    split
    0.41
    рены
    0.41
    じゃ
    0.41
    astica
    0.41
    ksam
    0.40
    ********/
    0.40
    火
    0.40
    Activations Density 0.001%

    No Known Activations