© 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. 71507
    Prev
    Next
    INDEX
    Explanations

    context

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

    context:

    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
    </b>
    0.89
    ät
    0.85
    </td>
    0.84
     accommodating
    0.79
    ’
    0.74
    ែ
    0.71
     opinions
    0.70
    ák
    0.70
    ä
    0.70
    ien
    0.68
    POSITIVE LOGITS
     kontek
    1.29
     contexto
    1.20
     контек
    1.20
     Context
    1.17
    context
    1.15
    ي
    1.15
     Kontext
    1.12
    Context
    1.11
     context
    1.07
    CONTEXT
    1.05
    Activations Density 0.013%

    No Known Activations