© 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. 148273
    Prev
    Next
    INDEX
    Explanations

    striving to, bell mushroom, Because I, freezing and

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

    lakehouse architecture

    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
     ankle
    0.51
     cor
    0.51
     .
    0.50
     enchant
    0.49
     anomaly
    0.47
     NGC
    0.46
     carpet
    0.46
     booties
    0.46
     boot
    0.45
     cans
    0.45
    POSITIVE LOGITS
    ម្រ
    0.54
    ❺
    0.52
    决赛
    0.46
     सुझा
    0.45
    支
    0.45
    专业
    0.45
    Ala
    0.45
    面白
    0.45
    িনবার্গ
    0.44
     मलाइका
    0.44
    Activations Density 0.000%

    No Known Activations