© 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. 80282
    Prev
    Next
    INDEX
    Explanations

    legal obligations

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

    rules, policy, power

    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
     checkpoints
    0.45
     สง
    0.43
     आगामी
    0.43
     checklists
    0.42
     सुकून
    0.41
    <0xAC>
    0.41
     मददगार
    0.40
    <0xB3>
    0.40
     esque
    0.39
     позволит
    0.39
    POSITIVE LOGITS
     vere
    0.50
    年的
    0.47
    jähr
    0.45
    Rama
    0.45
    нем
    0.44
     cowl
    0.44
     Erkrank
    0.44
     Vere
    0.43
     plötzlich
    0.43
    geteilt
    0.42
    Activations Density 0.000%

    No Known Activations