© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 98082
    Prev
    Next
    INDEX
    Explanations

    offer for

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

    `could be handled beautifully`

    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
     troubled
    0.44
    Ţ
    0.42
    individuals
    0.42
     bothered
    0.41
    ⁸
    0.41
     entstehen
    0.41
     vznik
    0.40
     biotechnology
    0.40
    RESULTS
    0.40
     perturbed
    0.40
    POSITIVE LOGITS
     redact
    0.47
     Jax
    0.46
    是为了
    0.44
     Por
    0.43
     Ol
    0.43
     Ox
    0.42
     reflexión
    0.41
    茅
    0.41
     recommand
    0.41
     upang
    0.40
    Activations Density 0.003%

    No Known Activations