© 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. 223866
    Prev
    Next
    INDEX
    Explanations

    problems or issues

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

    watch yourapple eaterpowers thatstate ruleswillingness togive you

    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
    -
    0.44
    ê
    0.43
    egrad
    0.42
    ico
    0.42
    ura
    0.41
    Growth
    0.40
    MAR
    0.40
    HEN
    0.40
    uda
    0.39
    N
    0.39
    POSITIVE LOGITS
     toxicology
    0.55
     biochemistry
    0.53
    ᱔
    0.52
     bacterias
    0.51
     biceps
    0.51
     bakteri
    0.51
     tongs
    0.51
     problems
    0.50
     जांच
    0.49
     problemas
    0.49
    Activations Density 0.001%

    No Known Activations