© 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. 89537
    Prev
    Next
    INDEX
    Explanations

    travel destinations and verdicts

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

    preventing twisting

    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
    ئیں۔
    0.51
     röm
    0.49
     stato
    0.49
    𝚃
    0.48
    ppet
    0.48
     بیٹ
    0.46
    넋
    0.46
     kabel
    0.46
     ônibus
    0.46
     تکمیل
    0.46
    POSITIVE LOGITS
     አለ
    0.47
     Следу
    0.46
    \
    0.43
    }}
    0.42
    ו
    0.41
    {
    0.41
     Che
    0.41
     Furthermore
    0.40
     cataly
    0.39
    vaart
    0.39
    Activations Density 0.000%

    No Known Activations