© 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. 20042
    Prev
    Next
    INDEX
    Explanations

    welche über occasionall

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

    lack of awareness or certainty

    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
     जिसे
    0.53
     जिसका
    0.47
    کار
    0.46
     전
    0.45
    전
    0.44
     یہ
    0.43
     이게
    0.43
     너
    0.42
     팀
    0.42
    NOW
    0.42
    POSITIVE LOGITS
    plicative
    0.46
    ographies
    0.44
    brane
    0.43
    apparent
    0.43
    éma
    0.43
    ocytes
    0.42
    wings
    0.42
    simpl
    0.41
    testimon
    0.40
    rások
    0.40
    Activations Density 0.000%

    No Known Activations