© 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. 193589
    Prev
    Next
    INDEX
    Explanations

    gas station

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

    strengths, asset, restricted, world

    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
    üler
    0.46
    ußer
    0.46
    üche
    0.45
    е
    0.45
    ippers
    0.45
     necklaces
    0.44
    ంబేద్
    0.43
     consequências
    0.43
    ä
    0.43
     cómo
    0.42
    POSITIVE LOGITS
    localized
    0.50
    力を
    0.43
     полі
    0.43
    ウト
    0.42
    わず
    0.41
    つまり
    0.40
    ਾਨੂੰ
    0.40
    ﺐ
    0.40
     genuinely
    0.39
    nueva
    0.39
    Activations Density 0.002%

    No Known Activations