© 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. 53631
    Prev
    Next
    INDEX
    Explanations

    a followed by specific word

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

    hypothetical or explainable scenarios

    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
    September
    0.46
    ൂപ
    0.45
    zné
    0.45
    Lincoln
    0.45
    त्म
    0.44
    把他
    0.43
    쁩
    0.42
    瀛
    0.41
    做
    0.41
    匪
    0.40
    POSITIVE LOGITS
    ları
    0.56
     Restoration
    0.49
     Rules
    0.49
     جہاں
    0.47
     Workspace
    0.46
     ";"
    0.46
     Conversations
    0.46
    ların
    0.45
    ēja
    0.45
    കുന്ന
    0.45
    Activations Density 0.000%

    No Known Activations