© 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. 195964
    Prev
    Next
    INDEX
    Explanations

    golden rule

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

    understanding concepts beyond math

    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
     બા
    0.48
    કડ
    0.47
    㖷
    0.47
     ቅ
    0.46
    कर्ताओं
    0.46
     शिक्षण
    0.46
     маг
    0.46
    Detective
    0.46
     કર્મચારી
    0.45
     миро
    0.45
    POSITIVE LOGITS
    -
    0.53
    et
    0.50
     ver
    0.50
    )]
    0.45
    ly
    0.44
     hesitation
    0.43
    doe
    0.43
    wn
    0.42
     agora
    0.42
     the
    0.42
    Activations Density 0.000%

    No Known Activations