© 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. 68346
    Prev
    Next
    INDEX
    Explanations

    certain mythological cryptographic terms

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

    avoid, believe, claim, loosen, insects

    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
    組成
    0.46
    ו
    0.46
     тобто
    0.45
    UIntValue
    0.45
    ן
    0.45
     ampere
    0.44
    𝐧
    0.43
     জানাতে
    0.42
    å
    0.42
     розподі
    0.42
    POSITIVE LOGITS
     certain
    0.45
    capi
    0.45
     முருக
    0.45
    Crypt
    0.45
    restrial
    0.45
    ெமி
    0.44
    Sq
    0.43
     mythological
    0.43
    པ
    0.43
    emus
    0.42
    Activations Density 0.000%

    No Known Activations