© 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. 105434
    Prev
    Next
    INDEX
    Explanations

    behavior shifts and advice

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

    longer sentences

    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
    at
    0.51
     இல்லை
    0.48
    Ferrari
    0.46
     Bayou
    0.44
     at
    0.44
    ‚
    0.44
    ka
    0.43
    ⛪
    0.43
    leq
    0.43
    Haven
    0.42
    POSITIVE LOGITS
     handleChange
    0.44
     programmes
    0.44
     mengajak
    0.44
     perturbations
    0.43
     bhai
    0.42
     ambas
    0.42
     citiz
    0.40
     sundry
    0.39
     enlist
    0.39
     Tatha
    0.39
    Activations Density 0.001%

    No Known Activations