© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 42581
    Prev
    Next
    INDEX
    Explanations

    ethical concerns and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jamás
    0.91
    <unused994>
    0.85
    <unused2148>
    0.84
    தந்திர
    0.84
    <unused503>
    0.82
    <unused433>
    0.81
     sepanjang
    0.81
    <unused2150>
    0.81
    <unused319>
    0.80
    <unused667>
    0.80
    POSITIVE LOGITS
    8
    1.24
    1
    1.22
    7
    1.20
    3
    1.16
    6
    1.15
    9
    1.14
    2
    1.09
    5
    1.06
    4
    1.06
    s
    0.99
    Activations Density 0.069%

    No Known Activations