© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5904
    Prev
    Next
    INDEX
    Explanations

    not allowed

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

    allowed and permissible

    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_53_width_65k_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
    ંભ
    0.39
    гора
    0.38
    âche
    0.38
    jeh
    0.37
    abang
    0.37
    ikten
    0.36
     responsabil
    0.36
    ᵑ
    0.36
    mlin
    0.35
     எதிர்க
    0.34
    POSITIVE LOGITS
     allowed
    3.63
     permitted
    3.63
    allowed
    3.45
     Allowed
    3.41
    Allowed
    3.30
     permissible
    3.23
    permitted
    3.23
     allowable
    3.16
    ALLOWED
    2.91
     permitido
    2.83
    Activations Density 0.159%

    No Known Activations