© 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. 168905
    Prev
    Next
    INDEX
    Explanations

    goal or objective explanation

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

    defend against attacks

    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
     Dink
    0.46
     शिखर
    0.44
     Bower
    0.42
     Magic
    0.41
    및
    0.41
     Giving
    0.40
     Listening
    0.40
    POWER
    0.40
    and
    0.40
    จะต้อง
    0.40
    POSITIVE LOGITS
     reticulum
    0.49
     penetrates
    0.47
    até
    0.47
    Cemento
    0.47
     worsens
    0.46
     molécule
    0.45
    𒌑
    0.45
    醞
    0.45
     alloying
    0.45
     chromospheres
    0.44
    Activations Density 0.002%

    No Known Activations