© 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. 188365
    Prev
    Next
    INDEX
    Explanations

    never get caught

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

    stunning architecture or scenery

    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
    лк
    0.49
    ove
    0.46
     autora
    0.45
    ᵚ
    0.45
    оне
    0.45
    ofd
    0.44
    oves
    0.43
    ッチ
    0.43
    mux
    0.43
    െടുത്ത
    0.43
    POSITIVE LOGITS
    ِينَ
    0.49
     thousand
    0.48
    记
    0.43
     neb
    0.42
     subcutaneous
    0.41
     in
    0.41
     vulnerable
    0.41
     conquering
    0.41
     delicious
    0.40
     enthusiastic
    0.40
    Activations Density 0.000%

    No Known Activations