© 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. 9054
    Prev
    Next
    INDEX
    Explanations

    intensity and direction

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

    force and direction

    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
     কাঠ
    0.40
    akad
    0.39
    ൽപ്പ
    0.37
    лер
    0.36
     струк
    0.36
    ń
    0.35
    类似
    0.34
    нд
    0.34
     клуб
    0.34
     kapcs
    0.33
    POSITIVE LOGITS
     intensity
    0.58
     direction
    0.56
     intensities
    0.51
    intensity
    0.51
     intensidad
    0.50
     directional
    0.49
     intensidade
    0.49
     magnitude
    0.48
     Intensity
    0.46
    Intensity
    0.46
    Activations Density 0.000%

    No Known Activations