© 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. 244119
    Prev
    Next
    INDEX
    Explanations

    reached a, old child, where if, booth fun

    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
    -
    0.55
                
    0.54
    Câu
    0.47
    <0x00>
    0.47
    acquisto
    0.46
              
    0.45
    Ancestor
    0.45
    Logo
    0.44
    しっかり
    0.44
    enko
    0.44
    POSITIVE LOGITS
     δι
    0.48
     vías
    0.44
     პირ
    0.43
     Гор
    0.42
     roadways
    0.42
     온
    0.41
    ந்த்
    0.41
     דר
    0.41
     કહ્યું
    0.40
     ਵ
    0.40
    Activations Density 0.000%

    No Known Activations